Reinforcement learning

Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.

6,934 stories · RSS feed

arXiv Machine Learning

Sep 10

Marginal-Contribution Policy Gradients under Filtered Feedback for Multi-Agent LLMs

arXiv:2604.22785v2 Announce Type: replace Abstract: We develop a unified treatment of credit assignment for RL training in multi-agent LLM systems. We show that observed reward alone cannot distingui...

By Elai Ben-Gal, Stela Tong

llms agents reinforcement-learning

arXiv Machine Learning

Sep 10

Environment Parameter Gradient Theorem for Co-Design in Reinforcement Learning

arXiv:2607.12590v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is traditionally concerned with learning a control policy for a fixed environment. In many engineering systems, h...

By Amber Srivastava

agents reinforcement-learning

arXiv Computation and Language

Sep 10

ConvMem: Convolutional Memory for Long-Context Reasoning

arXiv:2609.10441v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context l...

By Hongming Zhang, Zhaozhen Gu, Fengshuo Bai, Ming Hao, Qingyang Zhang, Yuanyuan Wang, Shiyang Tang, Yanna Wang, Bo Xu

llms reinforcement-learning

arXiv Computation and Language

Sep 10

MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation

arXiv:2510.05124v3 Announce Type: replace Abstract: We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS em...

By Mingjin Li, Yu Liu, Huayi Liu, Xiang Ye, Chao Jiang, Hongguang Zhang, Yu Ruan

llms agents reinforcement-learning

arXiv Computation and Language

Sep 10

Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective

arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explora...

By Shiqi Chen, Tongyao Zhu, Zian Wang, Jinghan Zhang, Kangrui Wang, Ruochen Zhou, Siyang Gao, Teng Xiao, Yee Whye Teh, Junxian He, Manling Li

llms agents reinforcement-learning fine-tuning

arXiv Statistics ML

Sep 10

RL unknotter, hard unknots and unknotting number

arXiv:2603.07955v4 Announce Type: replace-cross Abstract: We develop a reinforcement learning pipeline for simplifying knot diagrams. A trained agent learns move proposals and a value heuristic for n...

By Anne Dranowski, Yura Kabkov, Daniel Tubbenhauer

agents reinforcement-learning

arXiv AI

Sep 10

ExecCritic: Learn to Test, Test to Improve for Coding Agents

arXiv:2609.09133v1 Announce Type: new Abstract: Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agen...

By Leitian Tao, Baolin Peng, Haorui Wang, Hang Wang, Hao Cheng, Wenlin Yao, Qianhui Wu, Tao Ge, Sharon Li, Jianfeng Gao

llms agents reinforcement-learning

arXiv AI

Sep 10

Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference

arXiv:2609.05842v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards enables large language models to think slowly, but the same training can induce policy collapse: proba...

By Xiansheng Cai, Xiu-Hao Deng, Kun Chen

llms reinforcement-learning benchmarks

arXiv Machine Learning

Sep 10

Capsule Lens: Locating and Tracking Concept Geometry in Model Representations

arXiv:2609.05575v1 Announce Type: new Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability,...

By Yiming Tang, Harshvardhan Saini, Samyak Jha, Huaming Chen, Xufeng Duan, Dianbo Liu

nlp reinforcement-learning safety

arXiv AI

Sep 10

Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding

arXiv:2609.07107v1 Announce Type: new Abstract: Micro-dramas, characterized by ultra-short durations and hyper-dense storylines, pose unique challenges for video understanding that conventional bench...

By Yixin Qin, Shi-Zhe Chen, Zhiqi Yu, Siyuan Cheng, Tao Cheng, Jinwen Luo, Zheng Wei

reinforcement-learning benchmarks safety

arXiv AI

Sep 10

Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study

arXiv:2609.07998v1 Announce Type: new Abstract: We study the control of Markov decision processes in which the quality of a policy is evaluated by a dynamic, time-consistent Markov risk measure rathe...

By Aayush Patel, Andrzej Ruszczy\'nski

reinforcement-learning robotics safety

arXiv AI

Sep 10

Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement Learning

arXiv:2609.08025v1 Announce Type: new Abstract: Reasoning agents increasingly rely on external tools such as web search to answer complex queries. Reinforcement learning (RL) finetuning algorithms su...

By Vishwas Sathish, Viresh Ranjan, Xinliang Zhu, Arnab Dhua, Douglas Gray

llms agents nlp reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Sep 10

Inference-Time Nash Alignment

arXiv:2609.08082v1 Announce Type: new Abstract: Preference-based fine-tuning methods such as RLHF and DPO require substantial compute and large preference datasets. They also need direct access to th...

By Hadi Hosseini, Debmalya Mandal, Duohan Zhang

reinforcement-learning fine-tuning safety

arXiv Machine Learning

Sep 10

Local and Global Stability in Performative Reinforcement Learning

arXiv:2609.06467v1 Announce Type: new Abstract: In performative reinforcement learning the deployed policy shapes the environment that generates the learner's future data, and the natural solution co...

By Debmalya Mandal

agents reinforcement-learning

arXiv Machine Learning

Sep 10

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

arXiv:2609.07108v1 Announce Type: new Abstract: Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-training. Online co-training can furt...

By Zili Wang, Zhaopeng Qiu, Yuekai Zhang, Shuang Yu, Junjie Lai

reinforcement-learning

arXiv Machine Learning

Sep 10

Data Efficient Sample Selection for In-Context Learning

arXiv:2609.06670v1 Announce Type: new Abstract: The In-context learning (ICL) paradigm aids large language models (LLMs) to adapt to new tasks without need for fine-tuning. However, selecting an opti...

By V Venktesh, Cem levi, Avishek Anand

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Sep 10

Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment

arXiv:2609.08188v1 Announce Type: new Abstract: Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retriever...

By Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton

llms rag reinforcement-learning fine-tuning multimodal safety

arXiv Machine Learning

Sep 10

Learning Adaptive SED for heterogeneous load balancing

arXiv:2609.06881v1 Announce Type: new Abstract: We study a two-server load balancing system with heterogeneous service rates that are a priori unknown to the dispatcher. The goal is to route customer...

By Sanne van Kempen, Jaron Sanders, Fiona Sloothaak, Maarten G. Wolf

reinforcement-learning

arXiv AI

Sep 10

Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing

arXiv:2609.06484v1 Announce Type: cross Abstract: Planning with a generative model aims to estimate the value of a state using as few simulator calls as possible. SmoothCruiser achieves problem-indep...

By Tuan Dam

reinforcement-learning safety

arXiv AI

Sep 10

Power Mean Estimation in Stochastic Continuous Monte Carlo Tree Search

arXiv:2609.06489v1 Announce Type: cross Abstract: Monte Carlo Tree Search (MCTS) has demonstrated success in online planning for deterministic environments, yet significant challenges remain in adapt...

By Tuan Dam

reinforcement-learning

Get the daily briefing