Tootfinder

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Bingyu Yan, Ziyi Zhou, Xiaoming Zhang, Chaozhuo Li, Ruilin Zeng, Yirui Qi, Tianbo Wang, Litian Zhang
https://arxiv.org/abs/2508.03125

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct and overt persuasion, which limit their effectiveness, adaptability, and stealthiness. In this paper, we propose MAST, a Multi-round Adaptive Stealthy Tampering framework designed to exploit communic…

A gauge theory of complex adaptive systems
Gueorgui M. Mihaylov, Sergio L. Cacciatori
https://arxiv.org/abs/2509.01581 https://arxiv.org/pdf/2509.01581

A gauge theory of complex adaptive systems
We introduce a geometric construction of a gauge field theory of a complex adaptive system. It is based on a suitable simplicial formulation of a discrete geometry that manifests relevant properties valid in the classical differentiable case. Bundles' non-triviality naturally arises from local collective interactions between agents. Key elements of the theory of principal and associated bundles, such as local obstructions for triviality and characteristic classes, are opportunely defined in thi…

On the Perturbed Projection-Based Distributed Gradient-Descent Algorithm: A Fully-Distributed Adaptive Redesign
Tarek Bazizi, Mohamed Maghenem, Paolo Frasca, Antonio Lor\`ia, Elena Panteley
https://arxiv.org/abs/2509.03443

On the Perturbed Projection-Based Distributed Gradient-Descent Algorithm: A Fully-Distributed Adaptive Redesign
In this work, we revisit a classical distributed gradient-descent algorithm, introducing an interesting class of perturbed multi-agent systems. The state of each subsystem represents a local estimate of a solution to the global optimization problem. Thereby, the network is required to minimize local cost functions, while gathering the local estimates around a common value. Such a complex task suggests the interplay of consensus-based dynamics with gradient-descent dynamics. The latter descent d…

A Unified Perception-Language-Action Framework for Adaptive Autonomous Driving
Yi Zhang, Erik Leo Ha{\ss}, Kuo-Yi Chao, Nenad Petrovic, Yinglei Song, Chengdong Wu, Alois Knoll
https://arxiv.org/abs/2507.23540

A Unified Perception-Language-Action Framework for Adaptive Autonomous Driving
Autonomous driving systems face significant challenges in achieving human-like adaptability, robustness, and interpretability in complex, open-world environments. These challenges stem from fragmented architectures, limited generalization to novel scenarios, and insufficient semantic extraction from perception. To address these limitations, we propose a unified Perception-Language-Action (PLA) framework that integrates multi-sensor fusion (cameras, LiDAR, radar) with a large language model (LLM…

Adaptive Root Cause Localization for Microservice Systems with Multi-Agent Recursion-of-Thought
Lingzhe Zhang, Tong Jia, Kangjin Wang, Weijie Hong, Chiming Duan, Minghua He, Ying Li
https://arxiv.org/abs/2508.20370

Adaptive Root Cause Localization for Microservice Systems with Multi-Agent Recursion-of-Thought
As contemporary microservice systems become increasingly popular and complex-often comprising hundreds or even thousands of fine-grained, interdependent subsystems-they are facing more frequent failures. Ensuring system reliability thus demands accurate root cause localization. While traces and metrics have proven to be effective data sources for this task, existing methods either heavily rely on pre-defined schemas, which struggle to adapt to evolving operational contexts, or lack interpretabi…

Efficient rare event estimation for multimodal and high-dimensional system reliability via subset adaptive importance sampling
Sara Helal, Victor Elvira
https://arxiv.org/abs/2508.00210

Efficient rare event estimation for multimodal and high-dimensional system reliability via subset adaptive importance sampling
Estimating rare events in complex systems is a key challenge in reliability analysis. The challenge grows in multimodal problems, where traditional methods often rely on a small set of design points and risk overlooking critical failure modes. Further, higher dimensions make the probability mass harder to capture and demand substantially larger sample sizes to estimate failures. In this work, we propose a new sampling strategy, subset adaptive importance sampling (SAIS), that combines the stren…

Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
Yuanfang Xiang, Lun Ai
https://arxiv.org/abs/2510.00512 https://arxiv.org/pdf/2510.005…

Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
The transcriptional response to genetic perturbation reveals fundamental insights into complex cellular systems. While current approaches have made progress in predicting genetic perturbation responses, they provide limited biological understanding and cannot systematically refine existing knowledge. Overcoming these limitations requires an end-to-end integration of data-driven learning and existing knowledge. However, this integration is challenging due to inconsistencies between data and know…

The Indispensable Role of User Simulation in the Pursuit of AGI
Krisztian Balog, ChengXiang Zhai
https://arxiv.org/abs/2509.19456 https://arxiv.org/pdf/250…

The Indispensable Role of User Simulation in the Pursuit of AGI
Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive systems and acquiring the vast interaction data needed for training adaptive agents. This paper posits that user simulation -- creating computational agents that mimic human interaction with AI systems -- is not merely a useful tool, but is a critical catalyst required to overcome these bottlenecks and accelerate AGI development. We argue that realistic …

Self-organized learning emerges from coherent coupling of critical neurons
Chuanbo Liu, Jin Wang
https://arxiv.org/abs/2509.00107 https://arxiv.org/pdf/250…

Self-organized learning emerges from coherent coupling of critical neurons
Deep artificial neural networks have surpassed human-level performance across a diverse array of complex learning tasks, establishing themselves as indispensable tools in both social applications and scientific research. Despite these advances, the underlying mechanisms of training in artificial neural networks remain elusive. Here, we propose that artificial neural networks function as adaptive, self-organizing information processing systems in which training is mediated by the coherent co…

A Scalable Framework for Safety Assurance of Self-Driving Vehicles based on Assurance 2.0
Shufeng Chen, Mariat James Elizebeth, Robab Aghazadeh Chakherlou, Xingyu Zhao, Eric Barbier, Siddartha Khastgir, Paul Jennings
https://arxiv.org/abs/2510.00092

A Scalable Framework for Safety Assurance of Self-Driving Vehicles based on Assurance 2.0
Assurance 2.0 is a modern framework developed to address the assurance challenges of increasingly complex, adaptive, and autonomous systems. Building on the traditional Claims-Argument-Evidence (CAE) model, it introduces reusable assurance theories and explicit counterarguments (defeaters) to enhance rigor, transparency, and adaptability. It supports continuous, incremental assurance, enabling innovation without compromising safety. However, limitations persist in confidence measurement, residu…

Fast RLS Identification Leveraging the Linearized System Sparsity: Predictive Cost Adaptive Control for Quadrotors
Tam W. Nguyen
https://arxiv.org/abs/2508.17577 https://…

Fast RLS Identification Leveraging the Linearized System Sparsity: Predictive Cost Adaptive Control for Quadrotors
This paper presents a centralized predictive cost adaptive control (PCAC) strategy for the position and attitude control of quadrotors. PCAC is an optimal, prediction-based control method that uses recursive least squares (RLS) to identify model parameters online, enabling adaptability in dynamic environments. Addressing challenges with black-box approaches in systems with complex couplings and fast dynamics, this study leverages the unique sparsity of quadrotor models linearized around hover p…

OmniScene: Attention-Augmented Multimodal 4D Scene Understanding for Autonomous Driving
Pei Liu, Hongliang Lu, Haichao Liu, Haipeng Liu, Xin Liu, Ruoyu Yao, Shengbo Eben Li, Jun Ma
https://arxiv.org/abs/2509.19973

OmniScene: Attention-Augmented Multimodal 4D Scene Understanding for Autonomous Driving
Human vision is capable of transforming two-dimensional observations into an egocentric three-dimensional scene understanding, which underpins the ability to translate complex scenes and exhibit adaptive behaviors. This capability, however, remains lacking in current autonomous driving systems, where mainstream approaches primarily rely on depth-based 3D reconstruction rather than true scene understanding. To address this limitation, we propose a novel human-like framework called OmniScene. Fir…

Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
D. Veerababu, Ashwin A. Raikar, Prasanta K. Ghosh
https://arxiv.org/abs/2507.21749

Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made. The learning rate is one of such crucial hyperparameters, which is usually kept static during the training process. Learning dynamics in complex systems often requires a more adaptive approach to the learning rate. This adaptability becomes crucial to effecti…

RANGAN: GAN-empowered Anomaly Detection in 5G Cloud RAN
Douglas Liao, Jiping Luo, Jens Vevstad, Nikolaos Pappas
https://arxiv.org/abs/2508.20985 https://ar…

RANGAN: GAN-empowered Anomaly Detection in 5G Cloud RAN
Radio Access Network (RAN) systems are inherently complex, requiring continuous monitoring to prevent performance degradation and ensure optimal user experience. The RAN leverages numerous key performance indicators (KPIs) to evaluate system performance, generating vast amounts of data each second. This immense data volume can make troubleshooting and accurate diagnosis of performance anomalies more difficult. Furthermore, the highly dynamic nature of RAN performance demands adaptive methodolog…

Complex-valued Phase Synchrony Reveals Directional Coupling in FMRI and Tracks Medication Effects
Sir-Lord Wiafe, Najme Soleimani, Masoud Seraji, Bradley Baker, Robyn Miller, Ashkan Faghiri, Vince D. Calhoun
https://arxiv.org/abs/2509.13481

Complex-valued Phase Synchrony Reveals Directional Coupling in FMRI and Tracks Medication Effects
Understanding interactions in complex systems requires capturing the directionality of coupling, not only its strength. Phase synchronization captures this timing, yet most methods either reduce phase to its cosine or collapse it into scaler indices such as phase-locking value, discarding directionality. We propose a complex-valued phase synchrony (CVPS) framework that estimates phase with an adaptive Gabor wavelet and preserves both cosine and sine components. Simulations confirm that CVPS rec…

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
Binhao Wang, Yutian Xiao, Maolin Wang, Zhiqi Li, Tianshuo Wei, Ruocheng Guo, Xiangyu Zhao
https://arxiv.org/abs/2509.11094

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
Knowledge Graphs (KGs) enhance recommender systems but face challenges from inherent noise, sparsity, and Euclidean geometry's inadequacy for complex relational structures, critically impairing representation learning, especially for long-tail entities. Existing methods also often lack adaptive multi-source signal fusion tailored to item popularity. This paper introduces SPARK, a novel multi-stage framework systematically tackling these issues. SPARK first employs Tucker low-rank decomposition …

Comparison of Phase-Unwrapping Methods for Adaptive Optics Wavefront Sensing
D. Angelica Huerta, Justin R. Crepp, Caleb G. Abbott, Brian Joseph
https://arxiv.org/abs/2508.14167 …

Comparison of Phase-Unwrapping Methods for Adaptive Optics Wavefront Sensing
Advanced wavefront sensors (WFS) are essential for enabling new science cases for telescopes that utilize adaptive optics (AO) systems. While complex field WFS -- those that estimate the electric field phase and amplitude through interference or diffraction effects -- can achieve extraordinary sensitivity compared to existing devices, they typically reconstruct the wrapped phase of the measured wavefront, which must then be unwrapped for correction by continuous-surface deformable mirrors (DM).…

AF-RLIO: Adaptive Fusion of Radar-LiDAR-Inertial Information for Robust Odometry in Challenging Environments
Chenglong Qian, Yang Xu, Xiufang Shi, Jiming Chen, Liang Li
https://arxiv.org/abs/2507.18317

AF-RLIO: Adaptive Fusion of Radar-LiDAR-Inertial Information for Robust Odometry in Challenging Environments
In robotic navigation, maintaining precise pose estimation and navigation in complex and dynamic environments is crucial. However, environmental challenges such as smoke, tunnels, and adverse weather can significantly degrade the performance of single-sensor systems like LiDAR or GPS, compromising the overall stability and safety of autonomous robots. To address these challenges, we propose AF-RLIO: an adaptive fusion approach that integrates 4D millimeter-wave radar, LiDAR, inertial measuremen…

The Indispensable Role of User Simulation in the Pursuit of AGI
Krisztian Balog, ChengXiang Zhai
https://arxiv.org/abs/2509.19456 https://arxiv.org/pdf/250…

The Indispensable Role of User Simulation in the Pursuit of AGI
Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive systems and acquiring the vast interaction data needed for training adaptive agents. This paper posits that user simulation -- creating computational agents that mimic human interaction with AI systems -- is not merely a useful tool, but is a critical catalyst required to overcome these bottlenecks and accelerate AGI development. We argue that realistic …

Autonomous driving using an optimized neural network based adaptive LPV-MPC controller
Yassine Kebbati, Naima Ait-Oufroukh, Vicen\c{c} Puig, Vincent Vigneron, Dalil Ichalal
https://arxiv.org/abs/2509.19523

Autonomous driving using an optimized neural network based adaptive LPV-MPC controller
Driverless vehicles are complex systems operating in constantly changing environments. Automated driving is achieved by controlling the coupled longitudinal and lateral vehicle dynamics. Model predictive control is one of the most promising tools for this type of application due to its optimal performance and ability to handle constraints. This paper addresses autonomous driving with an adaptive linear parameter varying model predictive controller (LPV-MPC), which is adapted by a neural network…

MAGNeT: Multimodal Adaptive Gaussian Networks for Intent Inference in Moving Target Selection across Complex Scenarios
Xiangxian Li, Yawen Zheng, Baiqiao Zhang, Yijia Ma, XianhuiCao XianhuiCao, Juan Liu, Yulong Bian, Jin Huang, Chenglei Yang
https://arxiv.org/abs/2508.12992

MAGNeT: Multimodal Adaptive Gaussian Networks for Intent Inference in Moving Target Selection across Complex Scenarios
Moving target selection in multimedia interactive systems faces unprecedented challenges as users increasingly interact across diverse and dynamic contexts-from live streaming in moving vehicles to VR gaming in varying environments. Existing approaches rely on probabilistic models that relate endpoint distribution to target properties such as size and speed. However, these methods require substantial training data for each new context and lack transferability across scenarios, limiting their pr…

StepWrite: Adaptive Planning for Speech-Driven Text Generation
Hamza El Alaoui, Atieh Taheri, Yi-Hao Peng, Jeffrey P. Bigham
https://arxiv.org/abs/2508.04011 https://

StepWrite: Adaptive Planning for Speech-Driven Text Generation
People frequently use speech-to-text systems to compose short texts with voice. However, current voice-based interfaces struggle to support composing more detailed, contextually complex texts, especially in scenarios where users are on the move and cannot visually track progress. Longer-form communication, such as composing structured emails or thoughtful responses, requires persistent context tracking, structured guidance, and adaptability to evolving user intentions--capabilities that convent…

Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems
Dany Moshkovich, Sergey Zeltyn
https://arxiv.org/abs/2507.11277 …

Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems
Large Language Models (LLMs) are increasingly deployed within agentic systems-collections of interacting, LLM-powered agents that execute complex, adaptive workflows using memory, tools, and dynamic planning. While enabling powerful new capabilities, these systems also introduce unique forms of uncertainty stemming from probabilistic reasoning, evolving memory states, and fluid execution paths. Traditional software observability and operations practices fall short in addressing these challenges…

FLAIR: Feedback Learning for Adaptive Information Retrieval
William Zhang, Yiwen Zhu, Yunlei Lu, Mathieu Demarne, Wenjing Wang, Kai Deng, Nutan Sahoo, Katherine Lin, Miso Cilimdzic, Subru Krishnan
https://arxiv.org/abs/2508.13390

FLAIR: Feedback Learning for Adaptive Information Retrieval
Recent advances in Large Language Models (LLMs) have driven the adoption of copilots in complex technical scenarios, underscoring the growing need for specialized information retrieval solutions. In this paper, we introduce FLAIR, a lightweight, feedback learning framework that adapts copilot systems' retrieval strategies by integrating domain-specific expert feedback. FLAIR operates in two stages: an offline phase obtains indicators from (1) user feedback and (2) questions synthesized from doc…

LSDTs: LLM-Augmented Semantic Digital Twins for Adaptive Knowledge-Intensive Infrastructure Planning
Naiyi Li, Zihui Ma, Runlong Yu, Lingyao Li
https://arxiv.org/abs/2508.06799 …

LSDTs: LLM-Augmented Semantic Digital Twins for Adaptive Knowledge-Intensive Infrastructure Planning
Digital Twins (DTs) offer powerful tools for managing complex infrastructure systems, but their effectiveness is often limited by challenges in integrating unstructured knowledge. Recent advances in Large Language Models (LLMs) bring new potential to address this gap, with strong abilities in extracting and organizing diverse textual information. We therefore propose LSDTs (LLM-Augmented Semantic Digital Twins), a framework that helps LLMs extract planning knowledge from unstructured documents …

An Adaptive Port Technique for Synthesising Rotational Components in Component Modal Synthesis Approaches
Xiang Zhao, My Ha Dao
https://arxiv.org/abs/2507.03276

An Adaptive Port Technique for Synthesising Rotational Components in Component Modal Synthesis Approaches
Component Modal Synthesis (CMS) is a reduced order modelling method widely used for large-scale complex systems. It can effectively approximate system-level models through component synthesis, in which the repetitive geometrical components are modelled once and synthesised together. However, the conventional CMS only applies to systems with stationary components connected by strictly compatible ports, limiting it from modelling systems with moving components. This paper presents an adaptive por…

ProteuS: A Generative Approach for Simulating Concept Drift in Financial Markets
Andr\'es L. Su\'arez-Cetrulo, Alejandro Cervantes, David Quintana
https://arxiv.org/abs/2509.11844

ProteuS: A Generative Approach for Simulating Concept Drift in Financial Markets
Financial markets are complex, non-stationary systems where the underlying data distributions can shift over time, a phenomenon known as regime changes, as well as concept drift in the machine learning literature. These shifts, often triggered by major economic events, pose a significant challenge for traditional statistical and machine learning models. A fundamental problem in developing and validating adaptive algorithms is the lack of a ground truth in real-world financial data, making it di…

Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion
Yidan Lu, Rurui Yang, Qiran Kou, Mengting Chen, Tao Fan, Peter Cui, Yinzhao Dong, Peng Lu
https://arxiv.org/abs/2509.12858

Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion
Reinforcement learning has produced remarkable advances in humanoid locomotion, yet a fundamental dilemma persists for real-world deployment: policies must choose between the robustness of reactive proprioceptive control or the proactivity of complex, fragile perception-driven systems. This paper resolves this dilemma by introducing a paradigm that imbues a purely proprioceptive policy with proactive capabilities, achieving the foresight of perception without its deployment-time costs. Our core…

Adaptive Personalized Conversational Information Retrieval
Fengran Mo, Yuchen Hui, Yuxing Tian, Zhaoxuan Tan, Chuan Meng, Zhan Su, Kaiyu Huang, Jian-Yun Nie
https://arxiv.org/abs/2508.08634

Adaptive Personalized Conversational Information Retrieval
Personalized conversational information retrieval (CIR) systems aim to satisfy users' complex information needs through multi-turn interactions by considering user profiles. However, not all search queries require personalization. The challenge lies in appropriately incorporating personalization elements into search when needed. Most existing studies implicitly incorporate users' personal information and conversational context using large language models without distinguishing the specific requ…

Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation
Van-Khang Nguyen, Duc-Hoang Pham, Huy-Son Nguyen, Cam-Van Thi Nguyen, Hoang-Quynh Le, Duc-Trong Le
https://arxiv.org/abs/2508.08042

Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation
Recommendation systems have faced significant challenges in cold-start scenarios, where new items with a limited history of interaction need to be effectively recommended to users. Though multimodal data (e.g., images, text, audio, etc.) offer rich information to address this issue, existing approaches often employ simplistic integration methods such as concatenation, average pooling, or fixed weighting schemes, which fail to capture the complex relationships between modalities. Our study propo…

Dual-Stage Safe Herding Framework for Adversarial Attacker in Dynamic Environment
Wenqing Wang, Ye Zhang, Haoyu Li, Jingyu Wang
https://arxiv.org/abs/2509.08460 https://

Dual-Stage Safe Herding Framework for Adversarial Attacker in Dynamic Environment
Recent advances in robotics have enabled the widespread deployment of autonomous robotic systems in complex operational environments, presenting both unprecedented opportunities and significant security problems. Traditional shepherding approaches based on fixed formations are often ineffective or risky in urban and obstacle-rich scenarios, especially when facing adversarial agents with unknown and adaptive behaviors. This paper addresses this challenge as an extended herding problem, where def…

Programmable Locking Cells (PLC) for Modular Robots with High Stiffness Tunability and Morphological Adaptability
Jianshu Zhou, Wei Chen, Junda Huang, Boyuan Liang, Yunhui Liu, Masayoshi Tomizuka
https://arxiv.org/abs/2509.07916

Programmable Locking Cells (PLC) for Modular Robots with High Stiffness Tunability and Morphological Adaptability
Robotic systems operating in unstructured environments require the ability to switch between compliant and rigid states to perform diverse tasks such as adaptive grasping, high-force manipulation, shape holding, and navigation in constrained spaces, among others. However, many existing variable stiffness solutions rely on complex actuation schemes, continuous input power, or monolithic designs, limiting their modularity and scalability. This paper presents the Programmable Locking Cell (PLC)-a …

A Score-based Diffusion Model Approach for Adaptive Learning of Stochastic Partial Differential Equation Solutions
Toan Huynh, Ruth Lopez Fajardo, Guannan Zhang, Lili Ju, Feng Bao
https://arxiv.org/abs/2508.06834

A Score-based Diffusion Model Approach for Adaptive Learning of Stochastic Partial Differential Equation Solutions
We propose a novel framework for adaptively learning the time-evolving solutions of stochastic partial differential equations (SPDEs) using score-based diffusion models within a recursive Bayesian inference setting. SPDEs play a central role in modeling complex physical systems under uncertainty, but their numerical solutions often suffer from model errors and reduced accuracy due to incomplete physical knowledge and environmental variability. To address these challenges, we encode the governin…