Tootfinder

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Yi Liao, Yu Gu, Yuan Sui, Zining Zhu, Yifan Lu, Guohua Tang, Zhongqian Sun, Wei Yang
https://arxiv.org/abs/2508.21365

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Large language models (LLMs) excel at complex reasoning tasks such as mathematics and coding, yet they frequently struggle with simple interactive tasks that young children perform effortlessly. This discrepancy highlights a critical gap between declarative knowledge (knowing about something) and procedural knowledge (knowing how to do something). Although traditional reinforcement learning (RL) agents can acquire procedural knowledge through environmental interaction, they often operate as bla…

Reusable Test Suites for Reinforcement Learning
J{\o}rn Eirik Betten, Quentin Mazouni, Dennis Gross, Pedro Lind, Helge Spieker
https://arxiv.org/abs/2508.21553 https://

Reusable Test Suites for Reinforcement Learning
Reinforcement learning (RL) agents show great promise in solving sequential decision-making tasks. However, validating the reliability and performance of the agent policies' behavior for deployment remains challenging. Most reinforcement learning policy testing methods produce test suites tailored to the agent policy being tested, and their relevance to other policies is unclear. This work presents Multi-Policy Test Case Selection (MPTCS), a novel automated test suite selection method for RL en…

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
Vira Joshi, Zifan Xu, Bo Liu, Peter Stone, Amy Zhang
https://arxiv.org/abs/2507.23172 ht…

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy. At the same time, \emph{massively parallelized training} has gained popularity, not only for significantly accelerating data collection through GPU-accelerated simulation but also for enabling diverse data collection across multiple tasks by simulating heterogeneous scenes in p…

Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI
Dilruk Perera, Gousia Habib, Qianyi Xu, Daniel J. Tan, Kai He, Erik Cambria, Mengling Feng
https://arxiv.org/abs/2508.21101

Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI
Reinforcement learning (RL) marks a fundamental shift in how artificial intelligence is applied in healthcare. Instead of merely predicting outcomes, RL actively decides interventions with long term goals. Unlike traditional models that operate on fixed associations, RL systems learn through trial, feedback, and long-term reward optimization, introducing transformative possibilities and new risks. From an information fusion lens, healthcare RL typically integrates multi-source signals such as v…

Improving Aviation Safety Analysis: Automated HFACS Classification Using Reinforcement Learning with Group Relative Policy Optimization
Arash Ahmadi, Sarah Sharif, Yaser Banad
https://arxiv.org/abs/2508.21201

Improving Aviation Safety Analysis: Automated HFACS Classification Using Reinforcement Learning with Group Relative Policy Optimization
Analyzing the human factors behind aviation accidents is crucial for preventing future incidents, yet traditional methods using the Human Factors Analysis and Classification System (HFACS) are limited by scalability and consistency. To address this, we introduce an automated HFACS classification framework for aviation safety analysis that utilizes Reinforcement Learning with Group Relative Policy Optimization (GRPO) to fine-tune a Llama-3.1 8B language model. Our approach incorporates a multi-c…

Reinforcement Learning for Optimizing Large Qubit Array based Quantum Sensor Circuits
Laxmisha Ashok Attisara, Sathish Kumar
https://arxiv.org/abs/2508.21253 https://

Reinforcement Learning for Optimizing Large Qubit Array based Quantum Sensor Circuits
As the number of qubits in a sensor increases, the complexity of designing and controlling the quantum circuits grows exponentially. Manually optimizing these circuits becomes infeasible. Optimizing entanglement distribution in large-scale quantum circuits is critical for enhancing the sensitivity and efficiency of quantum sensors [5], [6]. This paper presents an engineering integration of reinforcement learning with tensor-network-based simulation (MPS) for scalable circuit optimization for op…

Offline Reinforcement Learning for Mobility Robustness Optimization
Pegah Alizadeh, Anastasios Giovanidis, Pradeepa Ramachandra, Vasileios Koutsoukis, Osama Arouk
https://arxiv.org/abs/2506.22793

Offline Reinforcement Learning for Mobility Robustness Optimization
In this work we revisit the Mobility Robustness Optimisation (MRO) algorithm and study the possibility of learning the optimal Cell Individual Offset tuning using offline Reinforcement Learning. Such methods make use of collected offline datasets to learn the optimal policy, without further exploration. We adapt and apply a sequence-based method called Decision Transformers as well as a value-based method called Conservative Q-Learning to learn the optimal policy for the same target reward as t…

This https://arxiv.org/abs/2308.13135 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Nonparametric Additive Value Functions: Interpretable Reinforcement Learning with an Application to Surgical Recovery
We propose a nonparametric additive model for estimating interpretable value functions in reinforcement learning, with an application in optimizing postoperative recovery through personalized, adaptive recommendations. While reinforcement learning has achieved significant success in various domains, recent methods often rely on black-box approaches such as neural networks, which hinder the examination of individual feature contributions to a decision-making policy. Our novel method offers a fle…

Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs
Minda Zhao
https://arxiv.org/abs/2508.21259 https://arxiv.org/pdf/2508…

Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs
Recommender systems struggle to provide accurate suggestions to new users with limited interaction history, a challenge known as the cold-user problem. This paper proposes a reinforcement learning approach using Double and Dueling Deep Q-Networks (DQN) to dynamically learn user preferences from sparse feedback, enhancing recommendation accuracy without relying on sensitive demographic data. By integrating these advanced DQN variants with a matrix factorization model, we achieve superior perform…

AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads
Taiyi Wang, Eiko Yoneki
https://arxiv.org/abs/2507.23084 https://arx…

AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads
Efficiently selecting indexes is fundamental to database performance optimization, particularly for systems handling large-scale analytical workloads. While deep reinforcement learning (DRL) has shown promise in automating index selection through its ability to learn from experience, few works address how these RL-based index advisors can adapt to scaling workloads due to exponentially growing action spaces and heavy trial and error. To address these challenges, we introduce AutoIndexer, a fram…

Causal-Inspired Multi-Agent Decision-Making via Graph Reinforcement Learning
Jing Wang, Yan Jin, Fei Ding, Chongfeng Wei
https://arxiv.org/abs/2507.23080 https://

Causal-Inspired Multi-Agent Decision-Making via Graph Reinforcement Learning
Since the advent of autonomous driving technology, it has experienced remarkable progress over the last decade. However, most existing research still struggles to address the challenges posed by environments where multiple vehicles have to interact seamlessly. This study aims to integrate causal learning with reinforcement learning-based methods by leveraging causal disentanglement representation learning (CDRL) to identify and extract causal features that influence optimal decision-making in a…

DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers
Navid Aftabi, Abhishek Hanchate, Satish Bukkapatnam, Dan Li
https://arxiv.org/abs/2508.21797

DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers
Industry 4.0's highly networked Machine Tool Controllers (MTCs) are prime targets for replay attacks that use outdated sensor data to manipulate actuators. Dynamic watermarking can reveal such tampering, but current schemes assume linear-Gaussian dynamics and use constant watermark statistics, making them vulnerable to the time-varying, partly proprietary behavior of MTCs. We close this gap with DynaMark, a reinforcement learning framework that models dynamic watermarking as a Markov decision p…

Fine-tuning for Data-enabled Predictive Control of Noisy Systems by Reinforcement Learning
Jinbao Wang, Shiliang Zhang, Jun Liu, Xuehui Ma, Haolin Liu
https://arxiv.org/abs/2505.24572

Fine-tuning for Data-enabled Predictive Control of Noisy Systems by Reinforcement Learning
Data-enabled predictive control (DeePC) leverages system measurements in characterizing system dynamics for optimal control. The performance of DeePC relies on optimizing its hyperparameters, especially in noisy systems where the optimal hyperparameters adapt over time. Existing hyperparameter tuning approaches for DeePC are more than often computationally inefficient or overly conservative. This paper proposes an adaptive DeePC where we guide its hyperparameters adaption through reinforcement …

Learning to Generate Unit Test via Adversarial Reinforcement Learning
Dongjun Lee, Changho Hwang, Kimin Lee
https://arxiv.org/abs/2508.21107 https://arxiv.…

Learning to Generate Unit Test via Adversarial Reinforcement Learning
Unit testing is a core practice in programming, enabling systematic evaluation of programs produced by human developers or large language models (LLMs). Given the challenges in writing comprehensive unit tests, LLMs have been employed to automate test generation, yet methods for training LLMs to produce high-quality tests remain underexplored. In this work, we propose UTRL, a novel reinforcement learning framework that trains an LLM to generate high-quality unit tests given a programming instru…

Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling
Bruce Fang, Danyi Gao
https://arxiv.org/abs/2507.00550 https:/…

Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling
This paper addresses the challenges of rapid resource variation and highly uncertain task loads in cloud computing environments. It proposes an optimization method for elastic cloud resource scaling based on a multi-agent system. The method deploys multiple autonomous agents to perceive resource states in parallel and make local decisions. While maintaining the distributed nature of the system, it introduces a collaborative value function to achieve global coordination. This improves the respon…

Control-Optimized Deep Reinforcement Learning for Artificially Intelligent Autonomous Systems
Oren Fivel, Matan Rudman, Kobi Cohen
https://arxiv.org/abs/2507.00268

Control-Optimized Deep Reinforcement Learning for Artificially Intelligent Autonomous Systems
Deep reinforcement learning (DRL) has become a powerful tool for complex decision-making in machine learning and AI. However, traditional methods often assume perfect action execution, overlooking the uncertainties and deviations between an agent's selected actions and the actual system response. In real-world applications, such as robotics, mechatronics, and communication networks, execution mismatches arising from system dynamics, hardware constraints, and latency can significantly degrade pe…

Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning
Xinyi Sheng, Dominik Baumann
https://arxiv.org/abs/2508.21443 https…

Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning
Reinforcement learning (RL) algorithms typically optimize the expected cumulative reward, i.e., the expected value of the sum of scalar rewards an agent receives over the course of a trajectory. The expected value averages the performance over an infinite number of trajectories. However, when deploying the agent in the real world, this ensemble average may be uninformative for the performance of individual trajectories. Thus, in many applications, optimizing the long-term performance of individ…

Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games
Ant\'onio Afonso, Iolanda Leite, Alessandro Sestini, Florian Fuchs, Konrad Tollmar, Linus Gissl\'en
https://arxiv.org/abs/2506.23626

Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games
Reinforcement Learning (RL) in games has gained significant momentum in recent years, enabling the creation of different agent behaviors that can transform a player's gaming experience. However, deploying RL agents in production environments presents two key challenges: (1) designing an effective reward function typically requires an RL expert, and (2) when a game's content or mechanics are modified, previously tuned reward weights may no longer be optimal. Towards the latter challenge, we prop…

Machine Intelligence on the Edge: Interpretable Cardiac Pattern Localisation Using Reinforcement Learning
Haozhe Tian, Qiyu Rao, Nina Moutonnet, Pietro Ferraro, Danilo Mandic
https://arxiv.org/abs/2508.21652

Machine Intelligence on the Edge: Interpretable Cardiac Pattern Localisation Using Reinforcement Learning
Matched filters are widely used to localise signal patterns due to their high efficiency and interpretability. However, their effectiveness deteriorates for low signal-to-noise ratio (SNR) signals, such as those recorded on edge devices, where prominent noise patterns can closely resemble the target within the limited length of the filter. One example is the ear-electrocardiogram (ear-ECG), where the cardiac signal is attenuated and heavily corrupted by artefacts. To address this, we propose th…

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
Xi Chen, Mingkang Zhu, Shaoteng Liu, Xiaoyang Wu, Xiaogang Xu, Yu Liu, Xiang Bai, Hengshuang Zhao
https://arxiv.org/abs/2506.22434

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
This work explores enabling Chain-of-Thought (CoT) reasoning to link visual cues across multiple images. A straightforward solution is to adapt rule-based reinforcement learning for Vision-Language Models (VLMs). However, such methods typically rely on manually curated question-answer pairs, which can be particularly challenging when dealing with fine grained visual details and complex logic across images. Inspired by self-supervised visual representation learning, we observe that images contai…

Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
Langming Liu, Wanyu Wang, Chi Zhang, Bo Li, Hongzhi Yin, Xuetao Wei, Wenbo Su, Bo Zheng, Xiangyu Zhao
https://arxiv.org/abs/2506.23090

Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
Online advertising in recommendation platforms has gained significant attention, with a predominant focus on channel recommendation and budget allocation strategies. However, current offline reinforcement learning (RL) methods face substantial challenges when applied to sparse advertising scenarios, primarily due to severe overestimation, distributional shifts, and overlooking budget constraints. To address these issues, we propose MTORL, a novel multi-task offline RL model that targets two key…

Deep reinforcement learning for efficient exploration of combinatorial structural design spaces
Chloe S. H. Hong, Keith J. Lee, Caitlin T. Mueller
https://arxiv.org/abs/2507.22804

Deep reinforcement learning for efficient exploration of combinatorial structural design spaces
This paper proposes a reinforcement learning framework for performance-driven structural design that combines bottom-up design generation with learned strategies to efficiently search large combinatorial design spaces. Motivated by the limitations of conventional top-down approaches such as optimization, the framework instead models structures as compositions of predefined elements, aligning form finding with practical constraints like constructability and component reuse. With the formulation …

Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation
Yusuke Tanaka, Alvin Zhu, Quanyou Wang, Dennis Hong
https://arxiv.org/abs/2507.00273

Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation
Reinforcement learning (RL) has enabled significant advances in humanoid robot locomotion, yet most learning frameworks do not account for mechanical intelligence embedded in parallel actuation mechanisms due to limitations in simulator support for closed kinematic chains. This omission can lead to inaccurate motion modeling and suboptimal policies, particularly for robots with high actuation complexity. This paper presents an end-to-end curriculum RL framework for BRUCE, a kid-sized humanoid r…

Hierarchical Adversarially-Resilient Multi-Agent Reinforcement Learning for Cyber-Physical Systems Security
Saad Alqithami
https://arxiv.org/abs/2506.22445

Hierarchical Adversarially-Resilient Multi-Agent Reinforcement Learning for Cyber-Physical Systems Security
Cyber-Physical Systems play a critical role in the infrastructure of various sectors, including manufacturing, energy distribution, and autonomous transportation systems. However, their increasing connectivity renders them highly vulnerable to sophisticated cyber threats, such as adaptive and zero-day attacks, against which traditional security methods like rule-based intrusion detection and single-agent reinforcement learning prove insufficient. To overcome these challenges, this paper introdu…

Explanations for Unrealizability of Infinite-State Safety Shields
Andoni Rodriguez, Irfansha Shaik, Davide Corsi, Roy Fox, Cesar Sanchez
https://arxiv.org/abs/2507.23603 https:/…

Explanations for Unrealizability of Infinite-State Safety Shields
Safe Reinforcement Learning focuses on developing optimal policies while ensuring safety. A popular method to address such task is shielding, in which a correct-by-construction safety component is synthesized from logical specifications. Recently, shield synthesis has been extended to infinite-state domains, such as continuous environments. This makes shielding more applicable to realistic scenarios. However, often shields might be unrealizable because the specification is inconsistent (e.g., c…

Med-R$^3$: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning
Keer Lu, Zheng Liang, Youquan Li, Jiejun Tan, Da Pan, Shusen Zhang, Guosheng Dong, Huang Leng
https://arxiv.org/abs/2507.23541

Med-R$^3$: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning
In medical scenarios, effectively retrieving external knowledge and leveraging it for rigorous logical reasoning is of significant importance. Despite their potential, existing work has predominantly focused on enhancing either retrieval or reasoning capabilities of the models in isolation, with little attention given to their joint optimization, which leads to limited coordination between the two processes. Additionally, current methods rely heavily on supervised fine-tuning (SFT), which can c…

Sources: Applied Compute, a pre-launch reinforcement learning startup founded by three former OpenAI staffers, raised $20M at a $100M valuation led by Benchmark (Alex Konrad/Upstarts Media)
https://www.upstartsmedia.com/p/ex-openai-applied-compute-raises-20m…

Ex-OpenAI Staffers Raise $20M For New Startup Applied Compute
The reinforcement learning startup founded by Rhythm Garg, Linden Li and Yash Patil was valued by VCs at Benchmark, Sequoia and others at $100 million pre-launch.

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
Harsh Goel, Mohammad Omama, Behdad Chalaki, Vaishnav Tadiparthi, Ehsan Moradi Pari, Sandeep Chinchali
https://arxiv.org/abs/2505.24265

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) has achieved significant progress in large-scale traffic control, autonomous vehicles, and robotics. Drawing inspiration from biological systems where roles naturally emerge to enable coordination, role-based MARL methods have been proposed to enhance cooperation learning for complex tasks. However, existing methods exclusively derive roles from an agent's past experience during training, neglecting their influence on its future trajectories. This paper…

A Knowledge Distillation-empowered Adaptive Federated Reinforcement Learning Framework for Multi-Domain IoT Applications Scheduling
Zhiyu Wang, Mohammad Goudarzi, Mingming Gong, Rajkumar Buyya
https://arxiv.org/abs/2508.21328

A Knowledge Distillation-empowered Adaptive Federated Reinforcement Learning Framework for Multi-Domain IoT Applications Scheduling
The rapid proliferation of Internet of Things (IoT) applications across heterogeneous Cloud-Edge-IoT environments presents significant challenges in distributed scheduling optimization. Existing approaches face issues, including fixed neural network architectures that are incompatible with computational heterogeneity, non-Independent and Identically Distributed (non-IID) data distributions across IoT scheduling domains, and insufficient cross-domain collaboration mechanisms. This paper proposes…

Crosslisted article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning
Allen Wang, Gavin Tao

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
Shaofei Cai, Zhancun Mu, Haiwen Xia, Bowei Zhang, Anji Liu, Yitao Liang
https://arxiv.org/abs/2507.23698

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL models is their tendency to overfit specific tasks or environments, thereby hindering the acquisition of generalizable behaviors across diverse settings. This paper provides a preliminary answer to this challenge by demonstrating that RL-finetuned visuomotor agents in Minecraft can achieve zero-shot generalization to unse…

This https://arxiv.org/abs/2505.19713 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGR_…

CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
In this work, we introduce CAD-Coder, a novel framework that reformulates text-to-CAD as the generation of CadQuery scripts - a Python-based, parametric CAD language. This representation enables direct geometric validation, a richer modeling vocabulary, and seamless integration with existing LLMs. To further enhance code validity and geometric fidelity, we propose a two-stage learning pipeline: (1) supervised fine-tuning on paired text-CadQuery data, and (2) reinforcement learning with Group Re…

A Reinforcement Learning Framework for Some Singular Stochastic Control Problems
Zongxia Liang, Xiaodong Luo, Xiang Yu
https://arxiv.org/abs/2506.22203 htt…

A Reinforcement Learning Framework for Some Singular Stochastic Control Problems
We develop a continuous-time reinforcement learning framework for a class of singular stochastic control problems without entropy regularization. The optimal singular control is characterized as the optimal singular control law, which is a pair of regions of time and the augmented states. The goal of learning is to identify such an optimal region via the trial-and-error procedure. In this context, we generalize the existing policy evaluation theories with regular controls to learn our optimal s…

Reliable Transmission of LTP Using Reinforcement Learning-Based Adaptive FEC
Liang Chen, Yu Song, Kanglian Zhao, Juan A. Fraire, Wenfeng Li
https://arxiv.org/abs/2506.22470

Reliable Transmission of LTP Using Reinforcement Learning-Based Adaptive FEC
Delay/Disruption Tolerant Networking (DTN) employs the Licklider Transmission Protocol (LTP) with Automatic Repeat reQuest (ARQ) for reliable data delivery in challenging interplanetary networks. While previous studies have integrated packet-level Forward Erasure Correction (FEC) into LTP to reduce retransmission time costs, existing static and delay-feedback-based dynamic coding methods struggle with highly variable and unpredictable deep space channel conditions. This paper proposes a reinfor…

Harnessing the Power of Reinforcement Learning for Adaptive MCMC
Congye Wang, Matthew A. Fisher, Heishiro Kanagawa, Wilson Chen, Chris. J. Oates
https://arxiv.org/abs/2507.00671

Harnessing the Power of Reinforcement Learning for Adaptive MCMC
Sampling algorithms drive probabilistic machine learning, and recent years have seen an explosion in the diversity of tools for this task. However, the increasing sophistication of sampling algorithms is correlated with an increase in the tuning burden. There is now a greater need than ever to treat the tuning of samplers as a learning task in its own right. In a conceptual breakthrough, Wang et al (2025) formulated Metropolis-Hastings as a Markov decision process, opening up the possibility fo…

Replaced article(s) found for stat.ME. https://arxiv.org/list/stat.ME/new
[2/2]:
- Semiparametric Double Reinforcement Learning with Applications to Long-Term Causal Inference
Lars van der Laan, David Hubbard, Allen Tran, Nathan Kallus, Aur\'elien Bibaut

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
Muzhi Dai, Shixuan Liu, Zhiyuan Zhao, Junyu Gao, Hao Sun, Xuelong Li
https://arxiv.org/abs/2507.22037

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
The rapid advancement of multimodal large language models (MLLMs) has led to breakthroughs in various applications, yet their security remains a critical challenge. One pressing issue involves unsafe image-query pairs--jailbreak inputs specifically designed to bypass security constraints and elicit unintended responses from MLLMs. Compared to general multimodal data, such unsafe inputs are relatively sparse, which limits the diversity and richness of training samples available for developing ro…

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control
Zijie Xu, Tong Bu, Zecheng Hao, Jianhao Ding, Zhaofei Yu
https://arxiv.org/abs/2505.24161

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control
Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making through neuromorphic hardware, making them compelling for Reinforcement Learning (RL) in resource-constrained edge devices. Recent studies in this field directly replace Artificial Neural Networks (ANNs) by SNNs in existing RL frameworks, overlooking whether the RL algorithm is suitable for SNNs. However, most RL algorithms in continuous control are designed tailored to ANNs, including the target network soft …

Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
Xiaolong Wei, Bo Lu, Xingyu Zhang, Zhejun Zhao, Dongdong Shen, Long Xia, Dawei Yin
https://arxiv.org/abs/2508.21476

Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use. Enhancing Small Language Models (SLMs) offers a promising alternative, but current methods like Supervised Fine-Tuning (SFT) struggle with novelty, and Reinforcement Learning from Human Feedback (RLHF) is costly. This paper explores two distinct AI-driven reward strategies within a Reinforcement Learning from AI Feedback (RLAIF) framework to…

Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
Guizhe Jin, Zhuoren Li, Bo Leng, Ran Yu, Lu Xiong
https://arxiv.org/abs/2506.23771

Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
Reinforcement Learning (RL) is increasingly used in autonomous driving (AD) and shows clear advantages. However, most RL-based AD methods overlook policy structure design. An RL policy that only outputs short-timescale vehicle control commands results in fluctuating driving behavior due to fluctuations in network outputs, while one that only outputs long-timescale driving goals cannot achieve unified optimality of driving behavior and control. Therefore, we propose a multi-timescale hierarchica…

Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning
Pascal R. van der Vaart, Neil Yorke-Smith, Matthijs T. J. Spaan
https://arxiv.org/abs/2508.21488 https://

Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning
Uncertainty quantification in reinforcement learning can greatly improve exploration and robustness. Approximate Bayesian approaches have recently been popularized to quantify uncertainty in model-free algorithms. However, so far the focus has been on improving the accuracy of the posterior approximation, instead of studying the accuracy of the prior and likelihood assumptions underlying the posterior. In this work, we demonstrate that there is a cold posterior effect in Bayesian deep Q-learnin…

Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction
Alex Durkin, Jasper Stolte, Matthew Jones, Raghuraman Pitchumani, Bei Li, Christian Michler, Mehmet Mercang\"oz
https://arxiv.org/abs/2507.22640

Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction
Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or costs of online experimentation. This work investigates the application of offline RL to the safe and efficient control of an exothermic polymerisation continuous stirred-tank reactor. We introduce a Gymnasium-compatible simulation environment that captures the reactor's nonlinear dynamics, including reaction kinetics,…

Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning
Pengcheng Dai, Yuanqiu Mo, Wenwu Yu, Wei Ren
https://arxiv.org/abs/2505.24113

Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning
This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer from poor expression due to linear function approximation, we propose a distributed neural policy gradient algorithm that features two innovatively designed neural networks, specifically for the approximate Q-functions and policy functions of agents. This distri…

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/1]:
- QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning
Allen Wang, Gavin Tao

Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems
Wenzheng Shu, Yanxiang Zeng, Yongxiang Tang, Teng Sha, Ning Luo, Yanhua Cheng, Xialong Liu, Fan Zhou, Peng Jiang
https://arxiv.org/abs/2506.22112

Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems
Offline reinforcement learning (RL) has emerged as a prevalent and effective methodology for real-world recommender systems, enabling learning policies from historical data and capturing user preferences. In offline RL, reward shaping encounters significant challenges, with past efforts to incorporate prior strategies for uncertainty to improve world models or penalize underexplored state-action pairs. Despite these efforts, a critical gap remains: the simultaneous balancing of intrinsic biases…

Learning to Drift with Individual Wheel Drive: Maneuvering Autonomous Vehicle at the Handling Limits
Yihan Zhou, Yiwen Lu, Bo Yang, Jiayun Li, Yilin Mo
https://arxiv.org/abs/2507.23339

Learning to Drift with Individual Wheel Drive: Maneuvering Autonomous Vehicle at the Handling Limits
Drifting, characterized by controlled vehicle motion at high sideslip angles, is crucial for safely handling emergency scenarios at the friction limits. While recent reinforcement learning approaches show promise for drifting control, they struggle with the significant simulation-to-reality gap, as policies that perform well in simulation often fail when transferred to physical systems. In this paper, we present a reinforcement learning framework with GPU-accelerated parallel simulation and sys…

Noise-Resilient Quantum Reinforcement Learning
Jing-Ci Yue, Jun-Hong An
https://arxiv.org/abs/2508.20601 https://arxiv.org/pdf/2508.20601

Noise-Resilient Quantum Reinforcement Learning
As a branch of quantum machine learning, quantum reinforcement learning (QRL) aims to solve complex sequential decision-making problems more efficiently and effectively than its classical counterpart by exploiting quantum resources. However, in the noisy intermediate-scale quantum (NISQ) era, its realization is challenged by the ubiquitous noise-induced decoherence. Here, we propose a noise-resilient QRL scheme for a quantum eigensolver. By investigating the non-Markovian decoherence effect on …

Laser Scan Path Design for Controlled Microstructure in Additive Manufacturing with Integrated Reduced-Order Phase-Field Modeling and Deep Reinforcement Learning
Augustine Twumasi, Prokash Chandra Roy, Zixun Li, Soumya Shouvik Bhattacharjee, Zhengtao Gan
https://arxiv.org/abs/2506.21815 …

Laser Scan Path Design for Controlled Microstructure in Additive Manufacturing with Integrated Reduced-Order Phase-Field Modeling and Deep Reinforcement Learning
Laser powder bed fusion (L-PBF) is a widely recognized additive manufacturing technology for producing intricate metal components with exceptional accuracy. A key challenge in L-PBF is the formation of complex microstructures affecting product quality. We propose a physics-guided, machine-learning approach to optimize scan paths for desired microstructure outcomes, such as equiaxed grains. We utilized a phase-field method (PFM) to model crystalline grain structure evolution. To reduce computati…

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/2]:
- Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settings
C. Shi, S. Zhang, W. Lu, R. Song

Single Agent Robust Deep Reinforcement Learning for Bus Fleet Control
Yifan Zhang
https://arxiv.org/abs/2508.20784 https://arxiv.org/pdf/2508.20784

Single Agent Robust Deep Reinforcement Learning for Bus Fleet Control
Bus bunching remains a challenge for urban transit due to stochastic traffic and passenger demand. Traditional solutions rely on multi-agent reinforcement learning (MARL) in loop-line settings, which overlook realistic operations characterized by heterogeneous routes, timetables, fluctuating demand, and varying fleet sizes. We propose a novel single-agent reinforcement learning (RL) framework for bus holding control that avoids the data imbalance and convergence issues of MARL under near-realis…

Toward Trusted Onboard AI: Advancing Small Satellite Operations using Reinforcement Learning
Cannon Whitney, Joseph Melville
https://arxiv.org/abs/2507.22198 https://

Toward Trusted Onboard AI: Advancing Small Satellite Operations using Reinforcement Learning
A RL (Reinforcement Learning) algorithm was developed for command automation onboard a 3U CubeSat. This effort focused on the implementation of macro control action RL, a technique in which an onboard agent is provided with compiled information based on live telemetry as its observation. The agent uses this information to produce high-level actions, such as adjusting attitude to solar pointing, which are then translated into control algorithms and executed through lower-level instructions. Once…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
- Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
Wang, Shao, Zhang, Yu, Liu, Ding, Cao, Kang, Wang

Learning to Assemble the Soma Cube with Legal-Action Masked DQN and Safe ZYZ Regrasp on a Doosan M0609
Jaehong Oh, Seungjun Jung, Sawoong Kim
https://arxiv.org/abs/2508.21272 ht…

Learning to Assemble the Soma Cube with Legal-Action Masked DQN and Safe ZYZ Regrasp on a Doosan M0609
This paper presents the first comprehensive application of legal-action masked Deep Q-Networks with safe ZYZ regrasp strategies to an underactuated gripper-equipped 6-DOF collaborative robot for autonomous Soma cube assembly learning. Our approach represents the first systematic integration of constraint-aware reinforcement learning with singularity-safe motion planning on a Doosan M0609 collaborative robot. We address critical challenges in robotic manipulation: combinatorial action space expl…

Spatial-Temporal Reinforcement Learning for Network Routing with Non-Markovian Traffic
Molly Wang
https://arxiv.org/abs/2507.22174 https://arxiv.org/pdf/25…

Spatial-Temporal Reinforcement Learning for Network Routing with Non-Markovian Traffic
Reinforcement Learning (RL) has become a well-established approach for optimizing packet routing in communication networks. Standard RL algorithms typically are based on the Markov Decision Process (MDP), which assumes that the current state of the environment provides all the necessary information for system evolution and decision-making. However, this Markovian assumption is invalid in many practical scenarios, making the MDP and RL frameworks inadequate to produce the optimal solutions. Addi…

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Yibin Wang, Zhimin Li, Yuhang Zang, Yujie Zhou, Jiazi Bu, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang
https://arxiv.org/abs/2508.20751

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images are susceptible to reward hacking. We reveal that this happens when minimal score differences between images are amplified after normalization, creating illusory advantages that drive the model to over-optimize for trivial gains, ultimately destabilizing the…

Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
Praveenkumar Katwe, Rakesh Chandra, Balabantaray Kali, Prasad Vittala
https://arxiv.org/abs/2507.22744

Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
Reducing hallucinations in abstractive summarization remains a critical challenge for deploying language models (LMs) in real-world settings. In this work, we introduce a rewarddriven fine-tuning framework that explicitly optimizes for Entity Hallucination Index (EHI), a metric designed to quantify the presence, correctness, and grounding of named entities in generated summaries. Given a corpus of meeting transcripts, we first generate baseline summaries using a pre-trained LM and compute EHI s…

Reactive Aerobatic Flight via Reinforcement Learning
Zhichao Han, Xijie Huang, Zhuxiu Xu, Jiarui Zhang, Yuze Wu, Mingyang Wang, Tianyue Wu, Fei Gao
https://arxiv.org/abs/2505.24396

Reactive Aerobatic Flight via Reinforcement Learning
Quadrotors have demonstrated remarkable versatility, yet their full aerobatic potential remains largely untapped due to inherent underactuation and the complexity of aggressive maneuvers. Traditional approaches, separating trajectory optimization and tracking control, suffer from tracking inaccuracies, computational latency, and sensitivity to initial conditions, limiting their effectiveness in dynamic, high-agility scenarios. Inspired by recent breakthroughs in data-driven methods, we propose …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/4]:
- Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
Haichao Zhang, We Xu, Haonan Yu

From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
Jie He, Victor Gutierrez Basulto, Jeff Z. Pan
https://arxiv.org/abs/2507.22716

From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
Reinforcement learning-based retrieval-augmented generation (RAG) methods enhance the reasoning abilities of large language models (LLMs). However, most rely only on final-answer rewards, overlooking intermediate reasoning quality. This paper analyzes existing RAG reasoning models and identifies three main failure patterns: (1) information insufficiency, meaning the model fails to retrieve adequate support; (2) faulty reasoning, where logical or content-level flaws appear despite sufficient inf…

Learning Agile Gate Traversal via Analytical Optimal Policy Gradient
Tianchen Sun, Bingheng Wang, Longbin Tang, Yichao Gao, Lin Zhao
https://arxiv.org/abs/2508.21592 https://

Learning Agile Gate Traversal via Analytical Optimal Policy Gradient
Traversing narrow gates presents a significant challenge and has become a standard benchmark for evaluating agile and precise quadrotor flight. Traditional modularized autonomous flight stacks require extensive design and parameter tuning, while end-to-end reinforcement learning (RL) methods often suffer from low sample efficiency and limited interpretability. In this work, we present a novel hybrid framework that adaptively fine-tunes model predictive control (MPC) parameters online using outp…

Homogenization of Multi-agent Learning Dynamics in Finite-state Markov Games
Yann Kerzreho (ENS Paris Saclay)
https://arxiv.org/abs/2506.21079 https://

Homogenization of Multi-agent Learning Dynamics in Finite-state Markov Games
This paper introduces a new approach for approximating the learning dynamics of multiple reinforcement learning (RL) agents interacting in a finite-state Markov game. The idea is to rescale the learning process by simultaneously reducing the learning rate and increasing the update frequency, effectively treating the agent's parameters as a slow-evolving variable influenced by the fast-mixing game state. Under mild assumptions-ergodicity of the state process and continuity of the updates-we prov…

X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
Zigang Geng, Yibing Wang, Yeyao Ma, Chen Li, Yongming Rao, Shuyang Gu, Zhao Zhong, Qinglin Lu, Han Hu, Xiaosong Zhang, Linus, Di Wang, Jie Jiang
https://arxiv.org/abs/2507.22058

X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through autoregressive modeling with discrete tokens have been plagued by issues such as low visual fidelity, distorted outputs, and failure to adhere to complex instructions when rendering intricate details. These shortcomings are likely attributed to cumulative errors duri…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/5]:
- QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning
Allen Wang, Gavin Tao

Reinforcement Learning for Optimal Control of Spin Magnetometers
Logan W. Cooke, Stefanie Czischek
https://arxiv.org/abs/2506.21475 https://

Reinforcement Learning for Optimal Control of Spin Magnetometers
Quantum optimal control in the presence of decoherence is difficult, particularly when not all Hamiltonian parameters are known precisely, as in quantum sensing applications. In this context, maximizing the sensitivity of the system is the objective, for which the optimal target state or unitary transformations are unknown, especially in the case of multi-parameter estimation. Here, we investigate the use of reinforcement learning (RL), specifically the soft actor-critic (SAC) algorithm, for pr…

Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidance
Kyanna Dagenais, Istvan David
https://arxiv.org/abs/2506.20883 https:…

Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidance
Model-driven engineering problems often require complex model transformations (MTs), i.e., MTs that are chained in extensive sequences. Pertinent examples of such problems include model synchronization, automated model repair, and design space exploration. Manually developing complex MTs is an error-prone and often infeasible process. Reinforcement learning (RL) is an apt way to alleviate these issues. In RL, an autonomous agent explores the state space through trial and error to identify benef…

This https://arxiv.org/abs/2505.20751 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Interactive OT Gym: A Reinforcement Learning-Based Interactive Optical tweezer (OT)-Driven Microrobotics Simulation Platform
Optical tweezers (OT) offer unparalleled capabilities for micromanipulation with submicron precision in biomedical applications. However, controlling conventional multi-trap OT to achieve cooperative manipulation of multiple complex-shaped microrobots in dynamic environments poses a significant challenge. To address this, we introduce Interactive OT Gym, a reinforcement learning (RL)-based simulation platform designed for OT-driven microrobotics. Our platform supports complex physical field sim…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/4]:
- BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement L...
Yunpeng Qing, Shuo Chen, Yixiao Chi, Shunyu Liu, Sixu Lin, Kelu Yao, Changqing Zou

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
Sihang Li, Wei Shi, Ziyuan Xie, Tao Liang, Guojun Ma, Xiang Wang
https://arxiv.org/abs/2507.00665

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely opaque. In this work, we present sparse Autoencoder For Enhanced Reward model (\textbf{SAFER}), a novel framework for interpreting and improving reward models through mechanistic analysis. Leveraging Sparse Autoencoders (SAEs), we uncover human-interpretable features in reward model activations, enabling insight into sa…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/5]:
- Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
Wang, Shao, Zhang, Yu, Liu, Ding, Cao, Kang, Wang

Crosslisted article(s) found for eess.SY. https://arxiv.org/list/eess.SY/new
[1/1]:
- QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning
Allen Wang, Gavin Tao

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/5]:
- Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Fe...
Chen, Shen, Huang, Zhou, Lin, Cai, Yu, Bu, Shi, Qiao

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
Carel van Niekerk, Renato Vukovic, Benjamin Matthias Ruppik, Hsien-chin Lin, Milica Ga\v{s}i\'c
https://arxiv.org/abs/2507.21931

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the model's own confidence as an intrinsic reward, mimicking how humans learn in the absence of external feedback. After a frozen LLM generates several chain-of-thought solutions, we define and compute the confidence of each final answer span and rank the traces ac…

Replicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model
Zixin Feng, Qunshan Zhao, Alison Heppenstall
https://arxiv.org/abs/2507.21341

Replicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model
Despite the rapid expansion of electric vehicle (EV) charging networks, questions remain about their efficiency in meeting the growing needs of EV drivers. Previous simulation-based approaches, which rely on static behavioural rules, have struggled to capture the adaptive behaviours of human drivers. Although reinforcement learning has been introduced in EV simulation studies, its application has primarily focused on optimising fleet operations rather than modelling private drivers who make ind…

Spiking Decision Transformers: Local Plasticity, Phase-Coding, and Dendritic Routing for Low-Power Sequence Control
Vishal Pandey, Debasmita Biswas
https://arxiv.org/abs/2508.21505

Spiking Decision Transformers: Local Plasticity, Phase-Coding, and Dendritic Routing for Low-Power Sequence Control
Reinforcement learning agents based on Transformer architectures have achieved impressive performance on sequential decision-making tasks, but their reliance on dense matrix operations makes them ill-suited for energy-constrained, edge-oriented platforms. Spiking neural networks promise ultra-low-power, event-driven inference, yet no prior work has seamlessly merged spiking dynamics with return-conditioned sequence modeling. We present the Spiking Decision Transformer (SNN-DT), which embeds Lea…

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
Yifan Wei, Xiaoyan Yu, Yixuan Weng, Tengfei Pan, Angsheng Li, Li Du
https://arxiv.org/abs/2507.21836 ht…

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools, but existing methods often rely on rigid, predefined tool-use patterns that risk degrading core language competence. Inspired by the human ability to adaptively select tools, we introduce AutoTIR, a reinforcement learning framework that enables LLMs to autonomo…

From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
Honglin He, Yukai Ma, Wayne Wu, Bolei Zhou
https://arxiv.org/abs/2507.22028 https:/…

From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
Navigation foundation models trained on massive webscale data enable agents to generalize across diverse environments and embodiments. However, these models trained solely on offline data, often lack the capacity to reason about the consequences of their actions or adapt through counterfactual understanding. They thus face significant limitations in the real-world urban navigation where interactive and safe behaviors, such as avoiding obstacles and moving pedestrians, are critical. To tackle th…

QoS-aware State-Augmented Learnable Algorithm for Wireless Coexistence Parameter Management
Mohammad Reza Fasihi, Brian L. Mark
https://arxiv.org/abs/2506.22652

QoS-aware State-Augmented Learnable Algorithm for Wireless Coexistence Parameter Management
Efficient and fair coexistence in unlicensed spectrum is essential to support heterogeneous networks such as 5G NR-U and Wi-Fi, which often contend for shared wireless resources. We introduce a general framework for wireless Coexistence Parameter Management (CPM) based on state-augmented constrained reinforcement learning. We propose a novel algorithm, QaSAL-CPM, which incorporates state-augmentation by embedding the dual variables in the constrained optimization formulation directly into the a…

AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
Lang Mei, Zhihan Yang, Chong Chen
https://arxiv.org/abs/2508.20368 https://

AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
Recent studies have explored integrating Large Language Models (LLMs) with search engines to leverage both the LLMs' internal pre-trained knowledge and external information. Specially, reinforcement learning (RL) has emerged as a promising paradigm for enhancing LLM reasoning through multi-turn interactions with search engines. However, existing RL-based search agents rely on a single LLM to handle both search planning and question-answering (QA) tasks in an end-to-end manner, which limits thei…

Linearly Decoding Refused Knowledge in Aligned Language Models
Aryan Shrivastava, Ari Holtzman
https://arxiv.org/abs/2507.00239 https://

Linearly Decoding Refused Knowledge in Aligned Language Models
Most commonly used language models (LMs) are instruction-tuned and aligned using a combination of fine-tuning and reinforcement learning, causing them to refuse users requests deemed harmful by the model. However, jailbreak prompts can often bypass these refusal mechanisms and elicit harmful responses. In this work, we study the extent to which information accessed via jailbreak prompts is decodable using linear probes trained on LM hidden states. We show that a great deal of initially refused …

Experimental investigation of pose informed reinforcement learning for skid-steered visual navigation
Ameya Salvi, Venkat Krovi
https://arxiv.org/abs/2506.21732

Experimental investigation of pose informed reinforcement learning for skid-steered visual navigation
Vision-based lane keeping is a topic of significant interest in the robotics and autonomous ground vehicles communities in various on-road and off-road applications. The skid-steered vehicle architecture has served as a useful vehicle platform for human controlled operations. However, systematic modeling, especially of the skid-slip wheel terrain interactions (primarily in off-road settings) has created bottlenecks for automation deployment. End-to-end learning based methods such as imitation l…

Cooperative Sensing Enhanced UAV Path-Following and Obstacle Avoidance with Variable Formation
Changheng Wang, Zhiqing Wei, Wangjun Jiang, Haoyue Jiang, Zhiyong Feng
https://arxiv.org/abs/2508.21316

Cooperative Sensing Enhanced UAV Path-Following and Obstacle Avoidance with Variable Formation
The high mobility of unmanned aerial vehicles (UAVs) enables them to be used in various civilian fields, such as rescue and cargo transport. Path-following is a crucial way to perform these tasks while sensing and collision avoidance are essential for safe flight. In this paper, we investigate how to efficiently and accurately achieve path-following, obstacle sensing and avoidance subtasks, as well as their conflict-free fusion scheduling. Firstly, a high precision deep reinforcement learning (…

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Haoran Luo, Haihong E, Guanting Chen, Qika Lin, Yikai Guo, Fangzhi Xu, Zemin Kuang, Meina Song, Xiaobao Wu, Yifan Zhu, Luu Anh Tuan
https://arxiv.org/abs/2507.21892

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, an agentic GraphRAG framework via end-to-end reinforcement …

Real-Time Energy Management Strategies for Community Microgrids
Moslem Uddin, Huadong Mo, Daoyi Dong
https://arxiv.org/abs/2506.22931 https://

Real-Time Energy Management Strategies for Community Microgrids
This study presents a real-time energy management framework for hybrid community microgrids integrating photovoltaic, wind, battery energy storage systems, diesel generators, and grid interconnection. The proposed approach formulates the dispatch problem as a multi-objective optimization task that aims to minimize operational costs. Two control strategies are proposed and evaluated: a conventional rule-based control (RBC) method and an advanced deep reinforcement learning (DRL) approach utilizi…

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
Quanfeng Lu, Zhantao Ma, Shuai Zhong, Jin Wang, Dahai Yu, Michael K. Ng, Ping Luo
https://arxiv.org/abs/2508.20018 …

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however, remain limited by structural constraints. Although multi-agent systems naturally decouple different competencies, recent progress in multi-agent reinforcement learning (MARL) has often been hindered by inefficiency and remains incompatible with current LVLM a…

Model Predictive Adversarial Imitation Learning for Planning from Observation
Tyler Han, Yanda Bao, Bhaumik Mehta, Gabriel Guo, Anubhav Vishwakarma, Emily Kang, Sanghun Jung, Rosario Scalise, Jason Zhou, Bryan Xu, Byron Boots
https://arxiv.org/abs/2507.21533

Model Predictive Adversarial Imitation Learning for Planning from Observation
Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function via Inverse Reinforcement Learning (IRL) then deploying this reward via Model Predictive Control (MPC). Towards unifying these methods, we derive a replacement of the policy in IRL with a planning-based agent. With connections to Adversarial Imitation Learnin…

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new
[2/2]:
- Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
Abdulaziz Almuzairee, Rohan Patil, Dwait Bhatt, Henrik I. Christensen

Double Check My Desired Return: Transformer with Target Alignment for Offline Reinforcement Learning
Yue Pei, Hongming Zhang, Chao Gao, Martin M\"uller, Mengxiao Zhu, Hao Sheng, Haogang Zhu, Liang Lin
https://arxiv.org/abs/2508.16420

Double Check My Desired Return: Transformer with Target Alignment for Offline Reinforcement Learning
Offline reinforcement learning (RL) has achieved significant advances in domains such as robotic control, autonomous driving, and medical decision-making. Most existing methods primarily focus on training policies that maximize cumulative returns from a given dataset. However, many real-world applications require precise control over policy performance levels, rather than simply pursuing the best possible return. Reinforcement learning via supervised learning (RvS) frames offline RL as a sequen…

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
https://arx…

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language can often provide a much richer learning medium for LLMs, compared with policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates …

A Hierarchical Signal Coordination and Control System Using a Hybrid Model-based and Reinforcement Learning Approach
Xianyue Peng, Shenyang Chen, H. Michael Zhang
https://arxiv.org/abs/2508.20102

A Hierarchical Signal Coordination and Control System Using a Hybrid Model-based and Reinforcement Learning Approach
Signal control in urban corridors faces the dual challenge of maintaining arterial traffic progression while adapting to demand variations at local intersections. We propose a hierarchical traffic signal coordination and control scheme that integrates model-based optimization with reinforcement learning. The system consists of: (i) a High-Level Coordinator (HLC) that selects coordination strategies based on observed and predicted demand; (ii) a Corridor Coordinator that derives phase constraint…

Libra: Assessing and Improving Reward Model by Learning to Think
Meng Zhou, Bei Li, Jiahao Liu, Xiaowen Shi, Yang Bai, Rongxiang Weng, Jingang Wang, Xunliang Cai
https://arxiv.org/abs/2507.21645

Libra: Assessing and Improving Reward Model by Learning to Think
Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based or reference-based rewards, which impose two critical limitations: 1) the dependence on finely annotated reference answer to attain rewards; and 2) the requirement for constrained output format. These limitations fundamentally hinder further RL data scaling an…

Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies
Hugo Garrido-Lestache, Jeremy Kedziora
https://arxiv.org/abs/2507.22782 https://

Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies
This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme incorporating multi-headed attention mechanisms in both the actor and critic. This design facilitates dynamic, inter-agent communication, allowing agents to explicitly query teammates, thereby efficiently managing the exponential growth of joint-action spaces while …

Active Query Selection for Crowd-Based Reinforcement Learning
Jonathan Erskine, Taku Yamagata, Ra\'ul Santos-Rodr\'iguez
https://arxiv.org/abs/2508.19132 https://…

Active Query Selection for Crowd-Based Reinforcement Learning
Preference-based reinforcement learning has gained prominence as a strategy for training agents in environments where the reward signal is difficult to specify or misaligned with human intent. However, its effectiveness is often limited by the high cost and low availability of reliable human input, especially in domains where expert feedback is scarce or errors are costly. To address this, we propose a novel framework that combines two complementary strategies: probabilistic crowd modelling to …

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Zengzhi Wang, Fan Zhou, Xuefeng Li, Pengfei Liu
https://arxiv.org/abs/2506.20512 http…

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Different base language model families, such as Llama and Qwen, exhibit divergent behaviors during post-training with reinforcement learning (RL), especially on reasoning-intensive tasks. What makes a base language model suitable for reinforcement learning? Gaining deeper insight into this question is essential for developing RL-scalable foundation models of the next generation. In this work, we investigate how mid-training strategies shape RL dynamics, focusing on two representative model fami…

DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
Shae McFadden, Myles Foley, Mario D'Onghia, Chris Hicks, Vasilios Mavroudis, Nicola Paoletti, Fabio Pierazzi
https://arxiv.org/abs/2508.18839

DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
Malware detection in real-world settings must deal with evolving threats, limited labeling budgets, and uncertain predictions. Traditional classifiers, without additional mechanisms, struggle to maintain performance under concept drift in malware domains, as their supervised learning formulation cannot optimize when to defer decisions to manual labeling and adaptation. Modern malware detection pipelines combine classifiers with monthly active learning (AL) and rejection mechanisms to mitigate t…

On the Definition of Intelligence
Kei-Sing Ng
https://arxiv.org/abs/2507.22423 https://arxiv.org/pdf/2507.22423

On the Definition of Intelligence
To engineer AGI, we should first capture the essence of intelligence in a species-agnostic form that can be evaluated, while being sufficiently general to encompass diverse paradigms of intelligent behavior, including reinforcement learning, generative models, classification, analogical reasoning, and goal-directed decision-making. We propose a general criterion based on sample fidelity: intelligence is the ability, given sample(s) from a category, to generate sample(s) from the same category. …

Task Allocation for Autonomous Machines using Computational Intelligence and Deep Reinforcement Learning
Thanh Thi Nguyen, Quoc Viet Hung Nguyen, Jonathan Kua, Imran Razzak, Dung Nguyen, Saeid Nahavandi
https://arxiv.org/abs/2508.20688

Task Allocation for Autonomous Machines using Computational Intelligence and Deep Reinforcement Learning
Enabling multiple autonomous machines to perform reliably requires the development of efficient cooperative control algorithms. This paper presents a survey of algorithms that have been developed for controlling and coordinating autonomous machines in complex environments. We especially focus on task allocation methods using computational intelligence (CI) and deep reinforcement learning (RL). The advantages and disadvantages of the surveyed methods are analysed thoroughly. We also propose and …

Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning
Yuyou Zhang, Radu Corcodel, Ding Zhao
https://arxiv.org/abs/2507.20382

Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning
Loco-manipulation of quadrupedal robots has broadened robotic applications, but using legs as manipulators often compromises locomotion, while mounting arms complicates the system. To mitigate this issue, we introduce bipedalism for quadrupedal robots, thus freeing the front legs for versatile interactions with the environment. We propose a risk-adaptive distributional Reinforcement Learning (RL) framework designed for quadrupedal robots walking on their hind legs, balancing worst-case conserva…

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Hinrich Sch\"utze, Volker Tresp, Yunpu Ma
https://arxiv.org/abs/2508.19828

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to address this limitation often augment LLMs with an external memory bank, yet most existing pipelines are static and heuristic-driven, lacking any learned mechanism for deciding what to store, update, or retrieve. We present Memory-R1, a reinforcement learning …

Impedance Primitive-augmented Hierarchical Reinforcement Learning for Sequential Tasks
Amin Berjaoui Tahmaz, Ravi Prakash, Jens Kober
https://arxiv.org/abs/2508.19607 https://…

Impedance Primitive-augmented Hierarchical Reinforcement Learning for Sequential Tasks
This paper presents an Impedance Primitive-augmented hierarchical reinforcement learning framework for efficient robotic manipulation in sequential contact tasks. We leverage this hierarchical structure to sequentially execute behavior primitives with variable stiffness control capabilities for contact tasks. Our proposed approach relies on three key components: an action space enabling variable stiffness control, an adaptive stiffness controller for dynamic stiffness adjustments during primiti…

ReCode: Updating Code API Knowledge with Reinforcement Learning
Haoze Wu, Yunzhi Yao, Wenhao Yu, Huajun Chen, Ningyu Zhang
https://arxiv.org/abs/2506.20495

ReCode: Updating Code API Knowledge with Reinforcement Learning
Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their training data, even with access to current documentation, impedes reliable code generation in dynamic environments. To tackle this issue, we propose ReCode (rule-based Reinforcement learning for Code Update), a novel framework that mimics human programmer adaptatio…