Tootfinder

Large longitudinal and anomalous transverse Magneto-thermoelectric effect in kagome antiferromagnet FeGe
Jiajun Ma, Rong Chen, Yazhou Li, Chenfei Shi, Yantao Cao, YuWei Zhang, Jiaxing Liao, Yunfei Han, Guangxi Wen, Jialu Wang, Hanjie Guo, Jianhui Dai, Chenguang Fu, Jin-Ke Bao, Yan Sun, Zhu-An Xu, Yuke Li
https://arxiv.org/abs/2511.21361

CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
Guo Qin, Zhi Chen, Yong Liu, Zhiyuan Shi, Haixuan Liu, Xiangdong Huang, Jianmin Wang, Mingsheng Long
https://arxiv.org/abs/2510.12681

CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
Time Series Foundation Models (TSFMs) have shown significant impact through their model capacity, scalability, and zero-shot generalization. However, due to the heterogeneity of inter-variate dependencies and the backbone scalability on large-scale multivariate datasets, most TSFMs are typically pre-trained on univariate time series. This limitation renders them oblivious to crucial information from diverse covariates in real-world forecasting tasks. To further enhance the performance of TSFMs,…

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Junhao Zhuang, Shi Guo, Xin Cai, Xiaohui Li, Yihao Liu, Chun Yuan, Tianfan Xue
https://arxiv.org/abs/2510.12747

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our goal in this work is to make diffusion-based VSR practical by achieving efficiency, scalability, and real-time performance. To this end, we propose FlashVSR, the first diffusion-based one-step streaming framework towards real-time VSR. FlashVSR runs at appro…

Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models
Rabimba Karanjai, Yang Lu, Ranjith Chodavarapu, Lei Xu, Weidong Shi
https://arxiv.org/abs/2510.12080

Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models
The rapid advancement of large language model (LLM) technology has led to diverse applications, many of which inherently require randomness, such as stochastic decision-making, gaming, scheduling, AI agents, and cryptography-related tasks. However, the capabilities of LLMs in handling randomness, particularly in generating and utilizing random numbers effectively, remain unclear. This paper investigates the capacity of LLMs for handling tasks that involve randomness through a series of experime…

Adding All Flavors: A Hybrid Random Number Generator for dApps and Web3
Ranjith Chodavarapu, Rabimba Karanjai, Xinxin Fan, Weidong Shi, Lei Xu
https://arxiv.org/abs/2510.12062 h…

Adding All Flavors: A Hybrid Random Number Generator for dApps and Web3
Random numbers play a vital role in many decentralized applications (dApps), such as gaming and decentralized finance (DeFi) applications. Existing random number provision mechanisms can be roughly divided into two categories, on-chain, and off-chain. On-chain approaches usually rely on the blockchain as the major input and all computations are done by blockchain nodes. The major risk for this type of method is that the input itself is susceptible to the adversary's influence. Off-chain…

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
Xin Gui, King Zhu, JinCheng Ren, Qianben Chen, Zekun Moore Wang, Yizhi LI, Xinpeng Liu, Xiaowan Li, Wenli Ren, Linyu Miao, Tianrui Qin, Ziqi Shu, He Zhu, Xiangru Tang, Dingfeng Shi, Jiaheng Liu, Yuchen Eleanor Jiang, Minghao Liu, Ge Zhang, Wangchunshu Zhou
https://

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
In recent years, the research focus of large language models (LLMs) and agents has shifted increasingly from demonstrating novel capabilities to complex reasoning and tackling challenging tasks. However, existing evaluations focus mainly on math/code contests or general tasks, while existing multi-domain academic benchmarks lack sufficient reasoning depth, leaving the field without a rigorous benchmark for high-level reasoning. To fill this gap, we introduce the Acadreason benchmark, designed t…

High-efficiency and long-distance quantum memory-assisted device-independent quantum secret sharing with single photon sources
Qi Zhang, Jia-Wei Ying, Shi-Pu Gu, Xing-Fu Wang, Lan Zhou, Yu-Bo Sheng
https://arxiv.org/abs/2510.12288

High-efficiency and long-distance quantum memory-assisted device-independent quantum secret sharing with single photon sources
Quantum secret sharing (QSS) plays a critical role in building the distributed quantum networks. Device-independent (DI) QSS provides the highest security level for QSS. However, the photon transmission loss and extremely low multipartite entanglement generation rate largely limit DI QSS's secure photon transmission distance and practical key generation efficiency. To address the above drawbacks, we propose the quantum memory-assisted (QMA) DI QSS protocol based on single photon sources (SPSs).…

Controlling Intent Expressiveness in Robot Motion with Diffusion Models
Wenli Shi, Clemence Grislain, Olivier Sigaud, Mohamed Chetouani
https://arxiv.org/abs/2510.12370 https://…

Controlling Intent Expressiveness in Robot Motion with Diffusion Models
Legibility of robot motion is critical in human-robot interaction, as it allows humans to quickly infer a robot's intended goal. Although traditional trajectory generation methods typically prioritize efficiency, they often fail to make the robot's intentions clear to humans. Meanwhile, existing approaches to legible motion usually produce only a single "most legible" trajectory, overlooking the need to modulate intent expressiveness in different contexts. In this work, we propose a novel motio…

Gauging the Competition: Understanding Social Comparison and Anxiety through Eye-tracking in Virtual Reality Group Interview
Shi-Ting Ni, Kairong Fang, Yuyang Wang, Pan Hui
https://arxiv.org/abs/2510.12590

Gauging the Competition: Understanding Social Comparison and Anxiety through Eye-tracking in Virtual Reality Group Interview
Virtual Reality (VR) is a promising tool for interview training, yet the psychological dynamics of group interviews, such as social comparison, remain underexplored. We investigate this phenomenon by developing an immersive VR group interview system and conducting an eye-tracking study with 73 participants. We manipulated peer performance using ambiguous behavioral cues (e.g., hand-raising) and objective information (public test scores) to measure their effect on participants' attention and sel…

Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
Meixia Lin, Meijiao Shi, Yunhai Xiao, Qian Zhang
https://arxiv.org/abs/2510.11546 http…

Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
High-dimensional regression often suffers from heavy-tailed noise and outliers, which can severely undermine the reliability of least-squares based methods. To improve robustness, we adopt a non-smooth Wilcoxon score based rank objective and incorporate structured group sparsity regularization, a natural generalization of the lasso, yielding a group lasso regularized rank regression method. By extending the tuning-free parameter selection scheme originally developed for the lasso, we introduce …

Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware
Jianan Mu, Mingyu Shi, Yining Wang, Tianmeng Yang, Bin Sun, Xing Hu, Jing Ye, Huawei Li
https://arxiv.org/abs/2510.08664

Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware
LLM-based RTL generation is an interesting research direction, as it holds the potential to liberate the least automated stage in the current chip design. However, due to the substantial semantic gap between high-level specifications and RTL, coupled with limited training data, existing models struggle with generation accuracy. Drawing on human experience, design with verification helps improving accuracy. However, as the RTL testbench data are even more scarce, it is not friendly for LLMs. Alt…

On higher regulators of Picard modular surfaces
Linli Shi
https://arxiv.org/abs/2510.08708 https://arxiv.org/pdf/2510.08708

On higher regulators of Picard modular surfaces
We prove the motivic classes in the motivic cohomology groups of Picard modular surfaces with non-trivial coefficients constructed in a paper of Loeffler\textendash Skinner\textendash Zerbes are in the motivic cohomology groups of the interior motives. Then we establish a relation between the motivic classes and non-critical values of the motivic $L$-functions associated to cuspidal automorphic representations of $\mathrm{GU}(2,1)$, thus deducing non-triviality of the motivic classes and provid…

Probabilistic Constellation Shaping for OFDM ISAC Signals Under Temporal-Frequency Filtering
Zhen Du, Jingjing Xu, Yifeng Xiong, Jie Wang, Musa Furkan Keskin, Henk Wymeersch, Fan Liu, Shi Jin
https://arxiv.org/abs/2510.12204

Probabilistic Constellation Shaping for OFDM ISAC Signals Under Temporal-Frequency Filtering
Integrated sensing and communications (ISAC) is considered an innovative technology in sixth-generation (6G) wireless networks, where utilizing orthogonal frequency division multiplexing (OFDM) communication signals for sensing provides a cost-effective solution for implementing ISAC. However, the sensing performance of matched and mismatched filtering schemes can be significantly deteriorated due to the signaling randomness induced by finite-alphabet modulations with nonconstant modulus, such …

Distributionally Robust Control with End-to-End Statistically Guaranteed Metric Learning
Jingyi Wu, Chao Ning, Yang Shi
https://arxiv.org/abs/2510.10214 https://

Distributionally Robust Control with End-to-End Statistically Guaranteed Metric Learning
Wasserstein distributionally robust control (DRC) recently emerges as a principled paradigm for handling uncertainty in stochastic dynamical systems. However, it constructs data-driven ambiguity sets via uniform distribution shifts before sequentially incorporating them into downstream control synthesis. This segregation between ambiguity set construction and control objectives inherently introduces a structural misalignment, which undesirably leads to conservative control policies with sub-opt…

Throughput Maximization for Multiuser Communications with Flexible-Sector 6DMA
Xiaoming Shi, Yunli Li, Xiaodan Shao, Jie Xu, Rui Zhang
https://arxiv.org/abs/2510.10944 https://

Throughput Maximization for Multiuser Communications with Flexible-Sector 6DMA
This paper presents a cost-effective and easily-deployable flexible-sector six-dimensional movable antenna (6DMA) architecture for future wireless communication networks, which enables flexible antenna configurations to match users' spatial distribution for capacity enhancement. Different from conventional sectorized base station (BS) with fixed-position antennas (FPAs), the flexible-sector 6DMA-enabled BS employs multiple directional sector antenna arrays that can flexibly move along a common …

Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR
Ling Sun, Charlotte Zhu, Shuju Shi
https://arxiv.org/abs/2510.10738 https://arxiv.org/…

Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR
General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper reduces average WER but simultaneously widens disparities and disproportionately harms lower-level learners. To address this, we propose two strategies: (i) proficiency-aware multitask learning, jointly optimizing ASR with proficiency classification, and (ii) targe…

On the Propagation and Damping of Alfvenic Fluctuations in the Outer Solar Corona and Solar Wind
Nikos Sioulas, Marco Velli, Chen Shi, Trevor A. Bowen, Alfred Mallet, Andrea Verdini, B. D. G. Chandran, Anna Tenerani, Jean-Baptiste Dakeyo, Stuart D. Bale, Davin Larson, Jasper S. Halekas, Lorenzo Matteini, Victor R\'eville, C. H. K. Chen, Orlando M. Romeo, Mingzhe Liu, Roberto Livi, Ali Rahmati, P. L. Whittlesey

On the Propagation and Damping of Alfvenic Fluctuations in the Outer Solar Corona and Solar Wind
We analyze \textit{Parker Solar Probe} and \textit{Solar Orbiter} observations to investigate the propagation and dissipation of Alfvénic fluctuations from the outer corona to 1~AU. Conservation of wave-action flux provides the theoretical baseline for how fluctuation amplitudes scale with the Alfvén Mach number $M_a$, once solar-wind acceleration is accounted for. Departures from this scaling quantify the net balance between energy injection and dissipation. Fluctuation amplitudes follow wav…

Studying the properties of reconnection-driven turbulence
Shi-Min Liang, Jian-Fu Zhang, Na-Na Gao, Nian-Yu Yi
https://arxiv.org/abs/2510.09978 https://arxi…

Studying the properties of reconnection-driven turbulence
Magnetic reconnection, often accompanied by turbulence interaction, is a ubiquitous phenomenon in astrophysical environments. However, the current understanding of the nature of turbulent magnetic reconnection remains insufficient. We investigate the statistical properties of reconnection turbulence in the framework of the self-driven reconnection. Using the open-source software package AMUN, we first perform numerical simulations of turbulent magnetic reconnection. We then obtain the statistic…

Noether-Type Inequalities for Big Divisors on Algebraic Surfaces
Shi Xu
https://arxiv.org/abs/2510.08089 https://arxiv.org/pdf/2510.08089

Noether-Type Inequalities for Big Divisors on Algebraic Surfaces
Let $D$ be a big integral divisor on a smooth projective surface $X$. In this paper, we study Noether-type inequalities for $D$. The key ingredient is the introduction of a numerical invariant $\mathfrak{e}(D)$, which depends only on the negative part $N$ of $D$. In particular, $\mathfrak{e}(D)=0$ if $D$ is nef. As an application, we establish an inequality between the volume and the pluri-sectional index of a canonical foliated surface of general type.

Evolutionary Computation as Natural Generative AI
Yaxin Shi, Abhishek Gupta, Ying Wu, Melvin Wong, Ivor Tsang, Thiago Rios, Stefan Menzel, Bernhard Sendhoff, Yaqing Hou, Yew-Soon Ong
https://arxiv.org/abs/2510.08590

Evolutionary Computation as Natural Generative AI
Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning based on local gradient signals. This often results in artifacts that are more derivative than genuinely generative. In contrast, Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity, expanding generative capabilities by exploring uncharted solution spaces beyond the limits …

Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
Heng Zhang, Tianyi Zhang, Yuling Shi, Xiaodong Gu, Yaomin Shen, Zijian Zhang, Yilei Yuan, Hao Zhang, Jin Huang
https://arxiv.org/abs/2510.12087

Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal similarity, assuming tighter coupling between graph and text representations improves transfer performance. However, our empirical analysis reveals that both natural gap expansion and forced gap reduction result in performance degradation by disrupting pre-tr…

Mean-field BSDEs with non-Lipschitz coefficients and double mean reflections
Li Hanwu, Shi Jin
https://arxiv.org/abs/2510.11228 https://arxiv.org/pdf/2510.…

Mean-field BSDEs with non-Lipschitz coefficients and double mean reflections
The present paper is devoted to the study of mean-field backward stochastic differential equations (MFBSDEs) with double mean reflections whose generators are not Lipschitz continuous. With the help of the Skorokhod problem and some a priori estimates for MFBSDEs, we establish the existence and uniqueness results for doubly mean reflected MFBSDEs.

Diffuse Laser Cooling Based on the $6\mathrm{P}_{3/2}$ Excited State of Rubidium Atoms via 420 nm Blue Light
Jia Zhang, Xun Gao Zheng Xiao, Xiaolei Guan Ruihang Chen, Mengyuan Han Tiantian Shi, Jingbiao Chen
https://arxiv.org/abs/2511.16220

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
Yi Liu, Yang Liu, Leqian Zheng, Jue Hong, Junjie Shi, Qingyou Yang, Ye Wu, Cong Wang
https://arxiv.org/abs/2510.12494

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
With the rapid advancement of the digital economy, data collaboration between organizations has become a well-established business model, driving the growth of various industries. However, privacy concerns make direct data sharing impractical. To address this, Two-Party Split Learning (a.k.a. Vertical Federated Learning (VFL)) has emerged as a promising solution for secure collaborative learning. Despite its advantages, this architecture still suffers from low computational resource utilization…

Light coupling to photonic integrated circuits using optimized lensed fibers
Dengke Chen, Zeying Zhong, Sanli Huang, Jiahao Sun, Sicheng Zeng, Baoqi Shi, Yi-Han Luo, Junqiu Liu
https://arxiv.org/abs/2510.10635

Light coupling to photonic integrated circuits using optimized lensed fibers
Efficient and reliable light coupling between optical fibers and photonic integrated circuits has arguably been the most essential issue in integrated photonics for optical interconnects, nonlinear signal conversion, neuromorphic computing, and quantum information processing. A commonly employed approach is to use inverse tapers interfacing with lensed fibers, particularly for waveguides of relatively low refractive index such as silicon nitride (Si3N4), silicon oxynitride and lithium niobate. …

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
Heng Zhang, Yuling Shi, Xiaodong Gu, Zijian Zhang, Haochen You, Lubin Gan, Yilei Yuan, Jin Huang
https://arxiv.org/abs/2510.10611

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) \textit{Ineffective group collaboration modeling}, as they rely on pairwise edge representations in graph structures, limiting their ability to capture relationships among multiple agents; and (ii) \textit{Limited task-adaptiveness in communication topology design}, leading to exces…

Underground Power Distribution System Restoration Using Inverter Based Resources
Wenlong Shi, Hongyi Li, Zhaoyu Wang
https://arxiv.org/abs/2510.08356 https://

Underground Power Distribution System Restoration Using Inverter Based Resources
Underground power distribution systems (PDSs) are increasingly deployed in urban areas. The integration of smart devices including smart switchgears, pad-mounted distribution transformers and inverter-based resources (IBRs) enhance system resilience, however simultaneously introducing unique challenges. The challenges include inrush currents caused by trapped charges in underground cables, ferroresonance in distribution transformers during energization, and three-phase load imbalance resulting …

Possible high-Tc superconductivity at 45 K in the Ge-doped cluster Mott insulator GaNb4Se8
Ji-Hai Yuan, Ya-Dong Gu, Yun-Qing Shi, Hao-Yu He, Qing-Song Liu, Jun-Kun Yi, Le-Wei Chen, Zheng-Xin Lin, Jia-Sheng Liu, Meng Wang, Zhi-An Ren
https://arxiv.org/abs/2510.12452

Possible high-Tc superconductivity at 45 K in the Ge-doped cluster Mott insulator GaNb4Se8
The Ge-doped GaNb4Se8 polycrystalline samples were synthesized by solid-state reaction method. Zero resistance transitions were observed in one batch of samples with the highest onset superconducting Tc at 45 K. This discovery may demonstrate a new class of Nb-based high-Tc superconductors arising from doped Mott insulators.

Dissecting the moat regime at low energies I: Renormalization and the phase structure
Fabian Rennecke, Shi Yin
https://arxiv.org/abs/2510.06712 https://arx…

Dissecting the moat regime at low energies I: Renormalization and the phase structure
Dense QCD matter can feature a moat regime, where the static energy of mesons is minimal at nonzero momentum. Valuable insights into this regime can be gained using low-energy models. This, however, requires a careful assessment of model artifacts. We therefore study the effects of renormalization and in-medium modifications of quark-meson interaction on the moat regime. To capture the main effects, we use a two-flavor quark-meson model at finite temperature and baryon density in the random pha…

Control variates from Eulerian and Lagrangian perturbation theory: Application to the bispectrum
Nickolas Kokron, Shi-Fan Chen
https://arxiv.org/abs/2510.07375 https://

Control variates from Eulerian and Lagrangian perturbation theory: Application to the bispectrum
Control variates have seen recent interest as a powerful technique to reduce the variance of summary statistics measured from costly cosmological $N$-body simulations. Of particular interest are the class of control variates which are analytically calculable, such as the recently introduced 'Zeldovich control variates' for the power spectrum of matter and biased tracers. In this work we present the construction of perturbative control variates in Eulerian and Lagrangian perturbation theory, and…

Crosslisted article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- Ivan-ISTD: Rethinking Cross-domain Heteroscedastic Noise Perturbations in Infrared Small Target D...
Yuehui Li, Yahao Lu, Haoyuan Wu, Sen Zhang, Liang Lin, Yukai Shi

Consistent gauge theories for the slave particle representation of the strongly correlated $t$-$J$ model
Xi Luo, Tao Shi, Yue Yu, Long Liang
https://arxiv.org/abs/2510.09264 htt…

Consistent gauge theories for the slave particle representation of the strongly correlated $t$-$J$ model
This note aims to clarify the confusion and inconsistency, and to address the incompleteness in our recent work [1,2]. In order to avoid the ill-defined nature of the free propagator of the gauge field in the ordered states of the $t$-$J$ model, we adopted a gauge fixing that was not of the Becchi-Rouet-Stora-Tyutin (BRST) exact form in our previous work [2]. This led to the situation where Dirac's second-class constraints, namely, the slave particle number constraint and the Ioffe-Larkin curre…

Replaced article(s) found for math.CO. https://arxiv.org/list/math.CO/new
[1/2]:
- Shi arrangements restricted to Weyl cones
Galen Dorpalen-Barry, Christian Stump

DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
Jinxin Shi, Zongsheng Cao, Runmin Ma, Yusong Hu, Jie Zhou, Xin Li, Lei Bai, Liang He, Bo Zhang
https://arxiv.org/abs/2510.08959

DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
The deep-research framework orchestrates external tools to perform complex, multi-step scientific reasoning that exceeds the native limits of a single large language model. However, it still suffers from context pollution, weak evidentiary support, and brittle execution paths. To address these issues, we propose DualResearch, a retrieval and fusion framework that matches the epistemic structure of tool-intensive reasoning by jointly modeling two complementary graphs: a breadth semantic graph th…

Mono4DEditor: Text-Driven 4D Scene Editing from Monocular Video via Point-Level Localization of Language-Embedded Gaussians
Jin-Chuan Shi, Chengye Su, Jiajun Wang, Ariel Shamir, Miao Wang
https://arxiv.org/abs/2510.09438

Mono4DEditor: Text-Driven 4D Scene Editing from Monocular Video via Point-Level Localization of Language-Embedded Gaussians
Editing 4D scenes reconstructed from monocular videos based on text prompts is a valuable yet challenging task with broad applications in content creation and virtual environments. The key difficulty lies in achieving semantically precise edits in localized regions of complex, dynamic scenes, while preserving the integrity of unedited content. To address this, we introduce Mono4DEditor, a novel framework for flexible and accurate text-driven 4D scene editing. Our method augments 3D Gaussians wi…

System Password Security: Attack and Defense Mechanisms
Chaofang Shi, Zhongwen Li, Xiaoqi Li
https://arxiv.org/abs/2510.10246 https://arxiv.org/pdf/2510.10…

System Password Security: Attack and Defense Mechanisms
System passwords serve as critical credentials for user authentication and access control when logging into operating systems or applications. Upon entering a valid password, users pass verification to access system resources and execute corresponding operations. In recent years, frequent password cracking attacks targeting system passwords have posed a severe threat to information system security. To address this challenge, in-depth research into password cracking attack methods and defensive …

Generative Multi-Sensory Meditation: Exploring Immersive Depth and Activation in Virtual Reality
Yuyang Jiang, Binzhu Xie, Lina Xu, Xiaokang Lei, Shi Qiu, Luwen Yu, Pan Hui
https://arxiv.org/abs/2510.11830

Generative Multi-Sensory Meditation: Exploring Immersive Depth and Activation in Virtual Reality
Mindfulness meditation has seen increasing applications in diverse domains as an effective practice to improve mental health. However, the standardized frameworks adopted by most applications often fail to cater to users with various psychological states and health conditions. This limitation arises primarily from the lack of personalization and adaptive content design. To address this, we propose MindfulVerse, an AI-Generated Content (AIGC)-driven application to create personalized and immersi…

Training-Free Group Relative Policy Optimization
Yuzheng Cai, Siqi Cai, Yuchen Shi, Zihan Xu, Lichao Chen, Yulei Qin, Xiaoyu Tan, Gang Li, Zongyi Li, Haojia Lin, Yong Mao, Ke Li, Xing Sun
https://arxiv.org/abs/2510.08191

Training-Free Group Relative Policy Optimization
Recent advances in Large Language Model (LLM) agents have demonstrated their promising general capabilities. However, their performance in specialized real-world domains often degrades due to challenges in effectively integrating external tools and specific prompting strategies. While methods like agentic reinforcement learning have been proposed to address this, they typically rely on costly parameter updates, for example, through a process that uses Supervised Fine-Tuning (SFT) followed by a …

Single-Shot Universality in Quantum LDPC Codes via Code-Switching
Shi Jie Samuel Tan, Yifan Hong, Ting-Chun Lin, Michael J. Gullans, Min-Hsiu Hsieh
https://arxiv.org/abs/2510.08552

Single-Shot Universality in Quantum LDPC Codes via Code-Switching
Code-switching is a powerful technique in quantum error correction that allows one to leverage the complementary strengths of different codes to achieve fault-tolerant universal quantum computation. However, existing code-switching protocols that encapsulate recent generalized lattice surgery approaches often either require many rounds of measurements to ensure fault-tolerance or suffer from low code rates. We present a single-shot, universal protocol that uses code-switching between high-rate …

Knowledge-Decoupled Functionally Invariant Path with Synthetic Personal Data for Personalized ASR
Yue Gu, Zhihao Du, Ying Shi, Jiqing Han, Yongjun He
https://arxiv.org/abs/2510.10401

Knowledge-Decoupled Functionally Invariant Path with Synthetic Personal Data for Personalized ASR
Fine-tuning generic ASR models with large-scale synthetic personal data can enhance the personalization of ASR models, but it introduces challenges in adapting to synthetic personal data without forgetting real knowledge, and in adapting to personal data without forgetting generic knowledge. Considering that the functionally invariant path (FIP) framework enables model adaptation while preserving prior knowledge, in this letter, we introduce FIP into synthetic-data-augmented personalized ASR mo…

Optimal binary codes from $\mathcal{C}_{D}$-codes over a non-chain ring
Ankit Yadav, Ritumoni Sarma, Anuj Kumar Bhagat
https://arxiv.org/abs/2510.09057 https://

Optimal binary codes from $\mathcal{C}_{D}$-codes over a non-chain ring
In \cite{shi2022few-weight}, Shi and Li studied $\mathcal{C}_D$-codes over the ring $\mathcal{R}:=\mathbb{F}_2[x,y]/\langle x^2, y^2, xy-yx\rangle$ and their binary Gray images, where $D$ is derived using certain simplicial complexes. We study the subfield codes $\mathcal{C}_{D}^{(2)}$ of $\mathcal{C}_{D}$-codes over $\mathcal{R},$ where $D$ is as in \cite{shi2022few-weight} and more. We find the Hamming weight distribution and the parameters of $\mathcal{C}_D^{(2)}$ for various $D$, and identi…

The Influence of Magnetic Complexity of Active Regions on Solar Wind Properties During Solar Cycles 23 and 24
Xinzheng Shi, Hui Fu, Zhenghua Huang, Limei Yan, Qi Liu, Lidong Xia
https://arxiv.org/abs/2510.08975

The Influence of Magnetic Complexity of Active Regions on Solar Wind Properties During Solar Cycles 23 and 24
Linking solar wind properties to the activities and characteristics of its source regions can enhance our understanding of its origin and generation mechanisms. Using the Mount Wilson magnetic classification (MWMC), we categorize all active regions (ARs) between 1999 and 2020 into three groups: alpha, beta, and complex ARs. Subsequently, we classify the near-Earth AR solar wind into the corresponding three types based on the magnetic type of ARs. Our results show that alpha, beta, and complex A…

RLinf-VLA: A Unified and Efficient Framework for VLA RL Training
Hongzhi Zang, Mingjie Wei, Si Xu, Yongji Wu, Zhen Guo, Yuanqing Wang, Hao Lin, Liangzhi Shi, Yuqing Xie, Zhexuan Xu, Zhihao Liu, Kang Chen, Wenhao Tang, Quanlu Zhang, Weinan Zhang, Chao Yu, Yu Wang
https://arxiv.org/abs/2510.06710

RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training
Recent progress in vision and language foundation models has significantly advanced multimodal understanding, reasoning, and generation, inspiring a surge of interest in extending such capabilities to embodied settings through vision-language-action (VLA) models. Yet, most VLA models are still trained with supervised fine-tuning (SFT), which struggles to generalize under distribution shifts due to error accumulation. Reinforcement learning (RL) offers a promising alternative by directly optimiz…

Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
Jinxiang Tu, Dayong Ren, Fei Shi, Zhenhong Jia, Yahong Ren, Jiwei Qin, Fang He
https://arxiv.org/abs/2510.09367

Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
Accurate forest biomass quantification is vital for carbon cycle monitoring. While airborne LiDAR excels at capturing 3D forest structure, directly estimating woody volume and Aboveground Biomass (AGB) from point clouds is challenging due to difficulties in modeling long-range dependencies needed to distinguish trees.We propose Minkowski-MambaNet, a novel deep learning framework that directly estimates volume and AGB from raw LiDAR. Its key innovation is integrating the Mamba model's Selective …

PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing
Jianhan Zhang, Jitao Wang, Chengchun Shi, John D. Piette, Donglin Zeng, Zhenke Wu
https://arxiv.org/abs/2510.06935

PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing
Reinforcement learning (RL) aims to learn and evaluate a sequential decision rule, often referred to as a "policy", that maximizes the population-level benefit in an environment across possibly infinitely many time steps. However, the sequential decisions made by an RL algorithm, while optimized to maximize overall population benefits, may disadvantage certain individuals who are in minority or socioeconomically disadvantaged groups. To address this problem, we introduce PyCFRL, a Python librar…

In-plane polar domains enhanced energy storage
Yu Lei, Xiaoming Shi, Sihan Yan, Qinghua Zhang, Jiecheng Liu, Sixu Wang, Yu Chen, Jiaou Wang, He Qi, Qian Li, Ting Lin, Jingfen Li, Qing Zhu, Haoyu Wang, Jing Chen, Lincong Shu, Linkun Wang, Han Wu, Xianran Xing
https://arxiv.org/abs/2510.11126

In-plane polar domains enhanced energy storage
Relaxor ferroelectric thin films are recognized for their ultrahigh power density, rendering them highly promising for energy storage applications in electrical and electronic systems. However, achieving high energy storage performance with chemically homogeneous, environmentally friendly and compositionally stable materials remains challenging. In this work, we present a design of dielectrics with high energy storage performance via an in-plane polar domains incorporating polar nanoregions mec…

Social Simulation for Integrating Self-Care: Measuring the Effects of Contextual Environments in Augmented Reality for Mental Health Practice
Anna Fang, Jiayang Shi, Hriday Chhabria, Bosi Li, Haiyi Zhu
https://arxiv.org/abs/2510.12081

Social Simulation for Integrating Self-Care: Measuring the Effects of Contextual Environments in Augmented Reality for Mental Health Practice
Despite growing interest in virtual and augmented reality (VR/AR) for mental well-being, prior work using immersive interventions to teach mental health skills has largely focused on calming or abstract settings. As a result, little is known about how realistic social simulation may better support the transfer and application of skills to in-person environments. In this work, we present a 14-day user study with 43-participants comparing an augmented reality intervention simulating a realistic c…

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Zonghao Ying, Yangguang Shao, Jianle Gan, Gan Xu, Junjie Shen, Wenxin Zhang, Quanchen Zou, Junzheng Shi, Zhenfei Yin, Mingchuan Zhang, Aishan Liu, Xianglong Liu
https://arxiv.org/abs/2510.10073

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security evaluation benchmarks. Existing benchmarks provide only partial coverage, typically restricted to narrow scenarios such as user-level prompt manipulation, and thus fail to capture the broad range of agent vulnerabilities. To address this gap, we present \tool{…

ConstraintLLM: A Neuro-Symbolic Framework for Industrial-Level Constraint Programming
Weichun Shi, Minghao Liu, Wanting Zhang, Langchen Shi, Fuqi Jia, Feifei Ma, Jian Zhang
https://arxiv.org/abs/2510.05774

ConstraintLLM: A Neuro-Symbolic Framework for Industrial-Level Constraint Programming
Constraint programming (CP) is a crucial technology for solving real-world constraint optimization problems (COPs), with the advantages of rich modeling semantics and high solving efficiency. Using large language models (LLMs) to generate formal modeling automatically for COPs is becoming a promising approach, which aims to build trustworthy neuro-symbolic AI with the help of symbolic solvers. However, CP has received less attention compared to works based on operations research (OR) models. We…

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair
Jos\'e Cambronero, Michele Tufano, Sherry Shi, Renyao Wei, Grant Uy, Runxiang Cheng, Chin-Jung Liu, Shiying Pan, Satish Chandra, Pat Rondon
https://arxiv.org/abs/2510.03217

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair
Agentic Automated Program Repair (APR) is increasingly tackling complex, repository-level bugs in industry, but ultimately agent-generated patches still need to be reviewed by a human before committing them to ensure they address the bug. Showing unlikely patches to developers can lead to substantial noise, wasting valuable developer time and eroding trust in automated code changes. We introduce two complementary LLM-based policies to reduce such noise: bug abstention and patch validation polic…

GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search
Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang
https://arxiv.org/abs/2510.10581

GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search
Multi-agent systems powered by Large Language Models excel at complex tasks through coordinated collaboration, yet they face high failure rates in multi-turn deep search scenarios. Existing temporal attribution methods struggle to accurately diagnose root causes, particularly when errors propagate across multiple agents. Attempts to automate failure attribution by analyzing action sequences remain ineffective due to their inability to account for information dependencies that span agents. This …

Twisted bi-layer magnetic photonic crystals
You-Ming Liu, Shi-Kai Lin, Pei-Shi Li, Yi-Ran Hao, Biao Yang
https://arxiv.org/abs/2510.07714 https://arxiv.org…

Twisted bi-layer magnetic photonic crystals
In photonics, twisted bi-layer systems have demonstrated unprecedented control over light-matter interactions, primarily through the modulation of photonic band structures and the formation of Moiré patterns. Meanwhile, magnetic photonic crystals have served as cornerstone platforms for manipulating light propagation, facilitating key applications such as Faraday rotation-based isolators and non-reciprocal devices. Nevertheless, the synergistic integration of twist engineering and magneto-opti…

Learning to Mitigate Post-Outage Load Surges: A Data-Driven Framework for Electrifying and Decarbonizing Grids
Wenlong Shi, Dingwei Wang, Liming Liu, Zhaoyu Wang
https://arxiv.org/abs/2510.08357

Learning to Mitigate Post-Outage Load Surges: A Data-Driven Framework for Electrifying and Decarbonizing Grids
Electrification and decarbonization are transforming power system demand and recovery dynamics, yet their implications for post-outage load surges remain poorly understood. Here we analyze a metropolitan-scale heterogeneous dataset for Indianapolis comprising 30,046 feeder-level outages between 2020 and 2024, linked to smart meters and submetering, to quantify the causal impact of electric vehicles (EVs), heat pumps (HPs) and distributed energy resources (DERs) on restoration surges. Statistica…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization a...
Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
https://arxiv.org/abs/2306.09158
- Sparse, Efficient and Explainable Data Attribution with DualXDA
Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
https://arxiv.org/abs/2402.12118 https://mastoxiv.page/@arXiv_csLG_bot/111962593972369958
- HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
Sun, Que, {\AA}rrestad, Loncar, Ngadiuba, Luk, Spiropulu
https://arxiv.org/abs/2405.00645 https://mastoxiv.page/@arXiv_csLG_bot/112370274737558603
- On the Identification of Temporally Causal Representation with Instantaneous Dependence
Li, Shen, Zheng, Cai, Song, Gong, Chen, Zhang
https://arxiv.org/abs/2405.15325 https://mastoxiv.page/@arXiv_csLG_bot/112511890051553111
- Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra
https://arxiv.org/abs/2405.15877 https://mastoxiv.page/@arXiv_csLG_bot/112517547424098076
- Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
Yan Shvartzshnaider, Vasisht Duddu
https://arxiv.org/abs/2409.03735 https://mastoxiv.page/@arXiv_csLG_bot/113089789682783135
- Low-Rank Filtering and Smoothing for Sequential Deep Learning
Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig
https://arxiv.org/abs/2410.06800 https://mastoxiv.page/@arXiv_csLG_bot/113283021321510736
- Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo, Qi Liu, Enhong Chen
https://arxiv.org/abs/2410.18686 https://mastoxiv.page/@arXiv_csLG_bot/113367101100828901
- Fairness via Independence: A (Conditional) Distance Covariance Framework
Ruifan Huang, Haixia Liu
https://arxiv.org/abs/2412.00720 https://mastoxiv.page/@arXiv_csLG_bot/113587817648503815
- Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
Simon Frieder, et al.
https://arxiv.org/abs/2412.15184 https://mastoxiv.page/@arXiv_csLG_bot/113683924322164777
- Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy
Ishank Juneja, Carlee Joe-Wong, Osman Ya\u{g}an
https://arxiv.org/abs/2501.10290 https://mastoxiv.page/@arXiv_csLG_bot/113859392622871057
- Towards Human-Guided, Data-Centric LLM Co-Pilots
Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat, Anders Boyd, Mihaela van der Schaar
https://arxiv.org/abs/2501.10321 https://mastoxiv.page/@arXiv_csLG_bot/113859392688054204
- Regularized Langevin Dynamics for Combinatorial Optimization
Shengyu Feng, Yiming Yang
https://arxiv.org/abs/2502.00277
- Generating Samples to Probe Trained Models
Eren Mehmet K{\i}ral, Nur\c{s}en Ayd{\i}n, \c{S}. \.Ilker Birbil
https://arxiv.org/abs/2502.06658 https://mastoxiv.page/@arXiv_csLG_bot/113984059089245671
- On Agnostic PAC Learning in the Small Error Regime
Julian Asilis, Mikael M{\o}ller H{\o}gsgaard, Grigoris Velegkas
https://arxiv.org/abs/2502.09496 https://mastoxiv.page/@arXiv_csLG_bot/114000974082372598
- Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo, Yongxu Zhu, Geoffrey Ye Li
https://arxiv.org/abs/2502.10784 https://mastoxiv.page/@arXiv_csLG_bot/114023667639951005
- On the Effect of Sampling Diversity in Scaling LLM Inference
Wang, Liu, Chen, Light, Liu, Chen, Zhang, Cheng
https://arxiv.org/abs/2502.11027 https://mastoxiv.page/@arXiv_csLG_bot/114023688225233656
- How to use score-based diffusion in earth system science: A satellite nowcasting example
Randy J. Chase, Katherine Haynes, Lander Ver Hoef, Imme Ebert-Uphoff
https://arxiv.org/abs/2505.10432 https://mastoxiv.page/@arXiv_csLG_bot/114516300594057680
- PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Christoffer Petersson, Daniel Persson, Jan E. Gerken
https://arxiv.org/abs/2505.17720 https://mastoxiv.page/@arXiv_csLG_bot/114572963019603744
- Train Sparse Autoencoders Efficiently by Utilizing Features Correlation
Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky
https://arxiv.org/abs/2505.22255 https://mastoxiv.page/@arXiv_csLG_bot/114589956040892075
- A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury, Basak Guler
https://arxiv.org/abs/2506.06486 https://mastoxiv.page/@arXiv_csLG_bot/114658421178857085
toXiv_bot_toot

Mid-Training of Large Language Models: A Survey
Kaixiang Mo, Yuxin Shi, Weiwei Weng, Zhiqiang Zhou, Shuman Liu, Haibo Zhang, Anxiang Zeng
https://arxiv.org/abs/2510.06826 https:…

Mid-Training of Large Language Models: A Survey
Large language models (LLMs) are typically developed through large-scale pre-training followed by task-specific fine-tuning. Recent advances highlight the importance of an intermediate mid-training stage, where models undergo multiple annealing-style phases that refine data quality, adapt optimization schedules, and extend context length. This stage mitigates diminishing returns from noisy tokens, stabilizes convergence, and expands model capability in late training. Its effectiveness can be ex…

Post-Quantum Security of Block Cipher Constructions
Gorjan Alagic, Chen Bai, Christian Majenz, Kaiyan Shi
https://arxiv.org/abs/2510.08725 https://arxiv.or…

Post-Quantum Security of Block Cipher Constructions
Block ciphers are versatile cryptographic ingredients that are used in a wide range of applications ranging from secure Internet communications to disk encryption. While post-quantum security of public-key cryptography has received significant attention, the case of symmetric-key cryptography (and block ciphers in particular) remains a largely unexplored topic. In this work, we set the foundations for a theory of post-quantum security for block ciphers and associated constructions. Leveraging o…

GO-Flock: Goal-Oriented Flocking in 3D Unknown Environments with Depth Maps
Yan Rui Tan, Wenqi Liu, Wai Lun Leong, John Guan Zhong Tan, Wayne Wen Huei Yong, Fan Shi, Rodney Swee Huat Teo
https://arxiv.org/abs/2510.05553

GO-Flock: Goal-Oriented Flocking in 3D Unknown Environments with Depth Maps
Artificial Potential Field (APF) methods are widely used for reactive flocking control, but they often suffer from challenges such as deadlocks and local minima, especially in the presence of obstacles. Existing solutions to address these issues are typically passive, leading to slow and inefficient collective navigation. As a result, many APF approaches have only been validated in obstacle-free environments or simplified, pseudo 3D simulations. This paper presents GO-Flock, a hybrid flocking f…

FlowSearch: Advancing deep research with dynamic structured knowledge flow
Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Xiangchao Yan, Wenlong Zhang, Lei Bai, Bo Zhang
https://arxiv.org/abs/2510.08521

FlowSearch: Advancing deep research with dynamic structured knowledge flow
Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for agentic systems. To address this, we propose FlowSearch, a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. FlowSearch is capable of strategically planning and expanding t…

Self-Speculative Masked Diffusions
Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet
https://arxiv.org/abs/2510.03929 https://arxiv.org/pdf/2…

Self-Speculative Masked Diffusions
We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked positions are then sampled, however, the factorization approximation means that sampling too many positions in one go leads to poor sample quality. As a result, many simulation steps and therefore n…

EigenScore: OOD Detection using Covariance in Diffusion Models
Shirin Shoushtari, Yi Wang, Xiao Shi, M. Salman Asif, Ulugbek S. Kamilov
https://arxiv.org/abs/2510.07206 https://…

EigenScore: OOD Detection using Covariance in Diffusion Models
Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems in safety-sensitive domains. Diffusion models have recently emerged as powerful generative models, capable of capturing complex data distributions through iterative denoising. Building on this progress, recent work has explored their potential for OOD detection. We propose EigenScore, a new OOD detection method that leverages the eigenvalue spectrum of the posterior covariance induced by a diffus…

Critical attention scaling in long-context transformers
Shi Chen, Zhengjiang Lin, Yury Polyanskiy, Philippe Rigollet
https://arxiv.org/abs/2510.05554 https://

Critical attention scaling in long-context transformers
As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity as context length $n$ increases, causing tokens to cluster excessively, a phenomenon known as rank-collapse. While $\textit{attention scaling}$ effectively addresses this deficiency by rescaling attention scores with a polylogarithmic factor $β_n$, theoretical justification for this approach remains lacking. We analyze a simplified yet tractable…

Quantum Zeno Effect in the Spatial Evolution of a Single Atom
Zheng-Yuan Zhang, Han-Chao Chen, Xin Liu, Li-Hua Zhang, Bang Liu, Shi-Yao Shao, Jun Zhang, Qi-Feng Wang, Qing Li, Yu Ma, Tian-Yu Han, Ya-Jun Wang, Dong-Yang Zhu, Jia-Dou Nan, Yi-Ming Yin, Qiao-Qiao Fang, Dong-Sheng Ding, Bao-Sen Shi
https://arxiv.org/abs/2509.24438

Quantum Zeno Effect in the Spatial Evolution of a Single Atom
The quantum Zeno effect (QZE) reveals that frequent measurements can suppress quantum evolution, but the detailed dynamics of the system under finite-duration measurements in experiments remain insufficiently explored. Here, we employ an optical dipole trap as a projective measurement to study the motion of a single cold atom in free space. By monitoring atomic loss, we directly observe the QZE in single-atom motion in free space and find that the effect of dipole measurements on the atom compr…

PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch
Shangjian Yin, Shining Liang, Wenbiao Ding, Yuli Qian, Zhouxing Shi, Hongzhi Li, Yutao Xie
https://arxiv.org/abs/2510.06670

PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch
Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs). However, its effectiveness depends on high-quality instruction data. Most existing alignment datasets are either private or require costly human annotation, which limits reproducibility and scalability. Even with Reinforcement Learning from AI Feedback (RLAIF), concerns about data quality remain. Moreover, it is unclear how much data is actually required to fine-tune a base mode…

D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems
Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang
https://arxiv.org/abs/2510.10585

D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems
Multi-agent systems powered by large language models exhibit strong capabilities in collaborative problem-solving. However, these systems suffer from substantial knowledge redundancy. Agents duplicate efforts in retrieval and reasoning processes. This inefficiency stems from a deeper issue: current architectures lack mechanisms to ensure agents share minimal sufficient information at each operational stage. Empirical analysis reveals an average knowledge duplication rate of 47.3\% across agent …

EMORL-TTS: Reinforcement Learning for Fine-Grained Emotion Control in LLM-based TTS
Haoxun Li, Yu Liu, Yuqing Sun, Hanlei Shi, Leyuan Qu, Taihao Li
https://arxiv.org/abs/2510.05758

EMORL-TTS: Reinforcement Learning for Fine-Grained Emotion Control in LLM-based TTS
Recent LLM-based TTS systems achieve strong quality and zero-shot ability, but lack fine-grained emotional control due to their reliance on discrete speech tokens. Existing approaches either limit emotions to categorical labels or cannot generalize to LLM-based architectures. We propose EMORL-TTS (Fine-grained Emotion-controllable TTS with Reinforcement Learning), a framework that unifies global intensity control in the VAD space with local emphasis regulation. Our method combines supervised fi…

LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models
Qingyuan Shi, Qingwen Meng, Hao Cheng, Qing Xu, Jianqiang Wang
https://arxiv.org/abs/2510.08046

LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models
The generation of testing and training scenarios for autonomous vehicles has drawn significant attention. While Large Language Models (LLMs) have enabled new scenario generation methods, current methods struggle to balance command adherence accuracy with the realism of real-world driving environments. To reduce scenario description complexity, these methods often compromise realism by limiting scenarios to 2D, or open-loop simulations where background vehicles follow predefined, non-interactive…

ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning
Siheng Zhao, Yanjie Ze, Yue Wang, C. Karen Liu, Pieter Abbeel, Guanya Shi, Rocky Duan
https://arxiv.org/abs/2510.05070

ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning
Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these policies lack the precision and object awareness required for loco-manipulation. To this end, we introduce ResMimic, a two-stage residual learning framework for precise and expressive humanoid control from human motion data. First, a GMT policy, trained on large-sc…

ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics
Luke Thompson, Davy Guan, Dai Shi, Slade Matthews, Junbin Gao, Andi Han
https://arxiv.org/abs/2510.05482 http…

ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics
Molecular dynamics (MD) simulations underpin modern computational drug dis- covery, materials science, and biochemistry. Recent machine learning models provide high-fidelity MD predictions without the need to repeatedly solve quantum mechanical forces, enabling significant speedups over conventional pipelines. Yet many such methods typically enforce strict equivariance and rely on sequential rollouts, thus limiting their flexibility and simulation efficiency. They are also com- monly single-tas…

Autonomy Matters: A Study on Personalization-Privacy Dilemma in LLM Agents
Zhiping Zhang, Yi Evie Zhang, Freda Shi, Tianshi Li
https://arxiv.org/abs/2510.04465 https://

Autonomy Matters: A Study on Personalization-Privacy Dilemma in LLM Agents
Large Language Model (LLM) agents require personal information for personalization in order to better act on users' behalf in daily tasks, but this raises privacy concerns and a personalization-privacy dilemma. Agent's autonomy introduces both risks and opportunities, yet its effects remain unclear. To better understand this, we conducted a 3$\times$3 between-subjects experiment ($N=450$) to study how agent's autonomy level and personalization influence users' privacy concerns, trust and willin…

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
Xiaochong Lan, Jie Feng, Yinxing Liu, Xinlei Shi, Yong Li
https://arxiv.org/abs/2510.08081

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
Ranking online reviews by their intrinsic quality is a critical task for e-commerce platforms and information services, impacting user experience and business outcomes. However, quality is a domain-dependent and dynamic concept, making its assessment a formidable challenge. Traditional methods relying on hand-crafted features are unscalable across domains and fail to adapt to evolving content patterns, while modern deep learning approaches often produce black-box models that lack interpretabili…

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
Dachuan Shi, Abedelkadir Asi, Keying Li, Xiangchi Yuan, Leyan Pan, Wenke Lee, Wen Xiao
https://arxiv.org/abs/2510.05069

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
Recent work shows that, beyond discrete reasoning through explicit chain-of-thought steps, which are limited by the boundaries of natural languages, large language models (LLMs) can also reason continuously in latent space, allowing richer information per step and thereby improving token efficiency. Despite this promise, latent reasoning still faces two challenges, especially in training-free settings: 1) purely latent reasoning broadens the search distribution by maintaining multiple implicit …

Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
Junchao Huang, Xinting Hu, Boyao Han, Shaoshuai Shi, Zhuotao Tian, Tianyu He, Li Jiang
https://arxiv.org/abs/2510.03198

Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfully simulate play, a model must generate natural content while exploring new scenes and preserve spatial consistency when revisiting explored areas. Under limited computation budgets, it must compress and exploit historical cues within a finite context window, which exposes a trade-off: Temporal-only memory lacks long…

Point Cloud-Based Control Barrier Functions for Model Predictive Control in Safety-Critical Navigation of Autonomous Mobile Robots
Faduo Liang, Yunfeng Yang, Shi-Lu Dai
https://arxiv.org/abs/2510.02885

Point Cloud-Based Control Barrier Functions for Model Predictive Control in Safety-Critical Navigation of Autonomous Mobile Robots
In this work, we propose a novel motion planning algorithm to facilitate safety-critical navigation for autonomous mobile robots. The proposed algorithm integrates a real-time dynamic obstacle tracking and mapping system that categorizes point clouds into dynamic and static components. For dynamic point clouds, the Kalman filter is employed to estimate and predict their motion states. Based on these predictions, we extrapolate the future states of dynamic point clouds, which are subsequently me…

NaturalEdit: Code Modification through Direct Interaction with Adaptive Natural Language Representation
Ningzhi Tang, David Meininger, Gelei Xu, Yiyu Shi, Yu Huang, Collin McMillan, Toby Jia-Jun Li
https://arxiv.org/abs/2510.04494

NaturalEdit: Code Modification through Direct Interaction with Adaptive Natural Language Representation
Code modification requires developers to comprehend code, plan changes, articulate intentions, and validate outcomes, making it a cognitively demanding process. Generated natural language code summaries aid comprehension but remain static and limited in supporting the full workflow. We present NaturalEdit, a system that makes code summaries interactive and adaptive representations directly linked to source code. Grounded in the Cognitive Dimensions of Notations, NaturalEdit implements a paradig…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/7]:
- Posterior Sampling for Continuing Environments
Wanqiao Xu, Shi Dong, Benjamin Van Roy

PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
Wanjia Zhao, Qinwei Ma, Jingzhe Shi, Shirley Wu, Jiaqi Han, Yijia Xiao, Si-Yuan Chen, Xiao Luo, Ludwig Schmidt, James Zou
https://arxiv.org/abs/2510.03185

PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks evaluate only final answers, which fail to capture reasoning processes, while recent stepwise methods rely on heuristic LLM-as-judge scoring or restrictive linear assumptions, limiting reliability and diagnostic validity. We introduce PRISM-Physics, a process-level evaluation framework and benchmark for complex physics r…

SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model
Yukai Shi, Weiyu Li, Zihao Wang, Hongyang Li, Xingyu Chen, Ping Tan, Lei Zhang
https://arxiv.org/abs/2512.10957

UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies
Harsh Gupta, Xiaofeng Guo, Huy Ha, Chuer Pan, Muqing Cao, Dongjae Lee, Sebastian Sherer, Shuran Song, Guanya Shi
https://arxiv.org/abs/2510.02614

UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies
We introduce UMI-on-Air, a framework for embodiment-aware deployment of embodiment-agnostic manipulation policies. Our approach leverages diverse, unconstrained human demonstrations collected with a handheld gripper (UMI) to train generalizable visuomotor policies. A central challenge in transferring these policies to constrained robotic embodiments-such as aerial manipulators-is the mismatch in control and robot dynamics, which often leads to out-of-distribution behaviors and poor execution. T…

Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representation
Yu-Zhe Shi, Qiao Xu, Yanjia Li, Mingchen Liu, Huamin Qu, Lecheng Ruan, Qining Wang
https://arxiv.org/abs/2510.02679

Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representation
Advanced Planning and Scheduling (APS) systems have become indispensable for modern manufacturing operations, enabling optimized resource allocation and production efficiency in increasingly complex and dynamic environments. While algorithms for solving abstracted scheduling problems have been extensively investigated, the critical prerequisite of specifying manufacturing requirements into formal constraints remains manual and labor-intensive. Although recent advances of generative models, part…

Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
Siddhant Arora, Jinchuan Tian, Hayato Futami, Jiatong Shi, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
https://arxiv.org/abs/2510.02066

Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
Most end-to-end (E2E) spoken dialogue systems (SDS) rely on voice activity detection (VAD) for turn-taking, but VAD fails to distinguish between pauses and turn completions. Duplex SDS models address this by predicting output continuously, including silence tokens, thus removing the need for explicit VAD. However, they often have complex dual-channel architecture and lag behind cascaded models in semantic reasoning. To overcome these challenges, we propose SCoT: a Streaming Chain-of-Thought (Co…

Can World Models Benefit VLMs for World Dynamics?
Kevin Zhang, Kuangzhi Ge, Xiaowei Chi, Renrui Zhang, Shaojun Shi, Zhen Dong, Sirui Han, Shanghang Zhang
https://arxiv.org/abs/2510.00855

Can World Models Benefit VLMs for World Dynamics?
Trained on internet-scale video data, generative world models are increasingly recognized as powerful world simulators that can generate consistent and plausible dynamics over structure, motion, and physics. This raises a natural question: with the advent of strong video foundational models, might they supplant conventional vision encoder paradigms for general-purpose multimodal understanding? While recent studies have begun to explore the potential of world models on common vision tasks, these…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/2]:
- Diagnosing and Mitigating System Bias in Self-Rewarding RL
Tan, Yuan, Wang, Li, Feng, Zhang, Shi, Zhang, Pan, Hu, Li

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[7/14]:
- QAMA: Scalable Quantum Annealing Multi-Head Attention Operator for Deep Learning
Peng Du, Jinjing Shi, Wenxuan Wang, Yin Ma, Kai Wen, Xuelong Li

Knowledge Distillation Detection for Open-weights Models
Qin Shi, Amber Yijia Zheng, Qifan Song, Raymond A. Yeh
https://arxiv.org/abs/2510.02302 https://ar…

Knowledge Distillation Detection for Open-weights Models
We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are available. This problem is motivated by growing concerns about model provenance and unauthorized replication through distillation. To address this task, we introduce a model-agnostic framework that combines data-free input synthesis and statistical score computation f…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/17]:
- Detecting Conspiracy Theory Against COVID-19 Vaccines
Md Hasibul Amin, Harika Madanu, Sahithi Lavu, Hadi Mansourifar, Dana Alsagheer, Weidong Shi

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
Hala Sheta, Eric Huang, Shuyu Wu, Ilia Alenabi, Jiajun Hong, Ryker Lin, Ruoxi Ning, Daniel Wei, Jialin Yang, Jiawei Zhou, Ziqiao Ma, Freda Shi
https://arxiv.org/abs/2510.02292

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermediate outputs from any layer during the forward pass of open-source VLMs. VLM-Lens provides a unified, YAML-configurable interface that abstracts away model-specific complexities and supports user-friendly operation across diverse VLMs. It currently supports 16 state-of-the-art base VLMs and their over 30 variants, and …

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
Jiayi Guo, Chuanhao Yan, Xingqian Xu, Yulin Wang, Kai Wang, Gao Huang, Humphrey Shi
https://arxiv.org/abs/2509.26231

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
Ensuring precise multimodal alignment between diffusion-generated images and input prompts has been a long-standing challenge. Earlier works finetune diffusion weight using high-quality preference data, which tends to be limited and difficult to scale up. Recent editing-based methods further refine local regions of generated images but may compromise overall image quality. In this work, we propose Implicit Multimodal Guidance (IMG), a novel re-generation-based multimodal alignment framework tha…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/8]:
- Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Genera...
Wu, Gao, Shi, Li, Xu, Zhang, Zhu, Wang, Luo, Wang, Wu, Huang

Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen, Shanyi Wang, Cixing Li, Wenxuan Wang, Zhaopeng Tu, Xiaolong Li, Zhaochun Ren, Linus
https://arxiv.org/abs/2510.01164

Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that guide these models when distributing scarce societal resources remain largely unexamined. To address this, we introduce the Social Welfare Function (SWF) Benchmark, a dynamic simulation environment where an LLM acts as a sovereign allocator, distributing tasks to a heterogeneous community of recipients. The benchmark is designed to create a persis…

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Cong Yu, Valter Uotila, Shilong Deng, Qingyuan Wu, Tuo Shi, Songlin Jiang, Lei You, Bo Zhao
https://arxiv.org/abs/2510.00967

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the…

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
Zeru Shi, Yingjia Wan, Zhenting Wang, Qifan Wang, Fan Yang, Elisa Kreiss, Ruixiang Tang
https://arxiv.org/abs/2510.01032

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
Motivated by the puzzling observation that inserting long sequences of meaningless tokens before the query prompt can consistently enhance LLM reasoning performance, this work analyzes the underlying mechanism driving this phenomenon and based on these insights proposes a more principled method that allows for similar performance gains. First, we find that the improvements arise from a redistribution of activations in the LLM's MLP layers, where near zero activations become less frequent while …

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
Jiayi Zhang, Simon Yu, Derek Chong, Anthony Sicilia, Michael R. Tomz, Christopher D. Manning, Weiyan Shi
https://arxiv.org/abs/2510.01171

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text as a result of well-established findings in cognitive psychology. We formalize this bias theoretically, verify it on preference datasets empirically, and show that it plays a cen…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/7]:
- Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
Zhang, Yu, Chong, Sicilia, Tomz, Manning, Shi

GEM: A Gym for Agentic LLMs
Zichen Liu, Anya Sims, Keyu Duan, Changyu Chen, Simon Yu, Xiangxin Zhou, Haotian Xu, Shaopan Xiong, Bo Liu, Chenmien Tan, Chuen Yang Beh, Weixun Wang, Hao Zhu, Weiyan Shi, Diyi Yang, Michael Shieh, Yee Whye Teh, Wee Sun Lee, Min Lin
https://arxiv.org/abs/2510.01051

GEM: A Gym for Agentic LLMs
The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environments. To facilitate this transition we introduce GEM (General Experience Maker), an open-source environment simulator designed for the age of LLMs. Analogous to OpenAI-Gym for traditional reinforcement learning (RL), GEM provides a standardized framework for the environment-agent interface, including asynchronous vec…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/8]:
- Centering Emotion Hotspots: Multimodal Local-Global Fusion and Cross-Modal Alignment for Emotion ...
Yu Liu, Hanlei Shi, Haoxun Li, Yuqing Sun, Yuxuan Ding, Linlin Gong, Leyuan Qu, Taihao Li

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
Yue Wang, Ruotian Ma, Xingyu Chen, Zhengliang Shi, Wanshun Chen, Huang Liu, Jiadi Yao, Qu Yang, Qingxuan Jiang, Fanghua Ye, Juntao Li, Min Zhang, Zhaopeng Tu, Xiaolong Li, Linus
https://arxiv.org/abs/2509.26514…

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
The rise of Large Language Models (LLMs) is reshaping multimodel models, with speech synthesis being a prominent application. However, existing approaches often underutilize the linguistic intelligence of these models, typically failing to leverage their powerful instruction-following capabilities. This limitation hinders the model's ability to follow text instructions for controllable Text-to-Speech~(TTS). To address this, we propose a new paradigm inspired by ``operationalism'' that decouples…

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Runze Liu, Jiakang Wang, Yuling Shi, Zhihui Xie, Chenxin An, Kaiyan Zhang, Jian Zhao, Xiaodong Gu, Lei Lin, Wenping Hu, Xiu Li, Fuzheng Zhang, Guorui Zhou, Kun Gai
https://arxiv.org/abs/2509.26628

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Reinforcement Learning (RL) has shown remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). Process-Supervised RL (PSRL) has emerged as a more effective paradigm compared to outcome-based RL. However, existing PSRL approaches suffer from limited exploration efficiency, both in terms of branching positions and sampling. In this paper, we introduce a novel PSRL framework (AttnRL), which enables efficient exploration for reasoning models. Motivated by prelimin…

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Cong Yu, Valter Uotila, Shilong Deng, Qingyuan Wu, Tuo Shi, Songlin Jiang, Lei You, Bo Zhao
https://arxiv.org/abs/2510.00967

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the…

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Yulei Qin, Xiaoyu Tan, Zhengbao He, Gang Li, Haojia Lin, Zongyi Li, Zihan Xu, Yuchen Shi, Siqi Cai, Renting Rui, Shaofei Cai, Yuzheng Cai, Xuan Zhang, Sheng Ye, Ke Li, Xing Sun
https://arxiv.org/abs/2509.22601

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL training instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation bala…

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
Siwei Wang, Yifei Shen, Haoran Sun, Shi Feng, Shang-Hua Teng, Li Dong, Yaru Hao, Wei Chen
https://arxiv.org/abs/2509.22613

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits and limitations through a tractable graph-based abstraction, focusing on policy gradient (PG) and Q-learning methods. Our theoretical analyses reveal that supervised fine-tuning (SFT) may introduce co-occurrence-based spurious solutions, whereas RL achieves c…