Reinforcement learning

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

6,685 stories · RSS feed

arXiv AI

Oct 15

Adaptive-Group Process Rewards for GUI Agents

arXiv:2610.17710v1 Announce Type: new Abstract: Training graphical user interface (GUI) agents with reinforcement learning suffers from sparse outcome rewards, leading to inefficient learning. Proces...

By Zirui Shang, Yang Liu, Xin Shu, Zhi Gao, Xinxiao Wu, Lifeng Fan

agents reinforcement-learning benchmarks

arXiv Machine Learning

Oct 15

Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following

arXiv:2610.19525v1 Announce Type: new Abstract: Verifiable instruction-following benchmarks emphasize output-constraint satisfaction but can overlook whether responses meaningfully answer the underly...

By Sangyeon Yoon, Wooseok Seo, Hamish Ivison, Hyesoo Hong, Donghoon Kim, Wonjun Kang, Albert No, Jaehyung Kim

reinforcement-learning benchmarks

arXiv AI

Oct 15

Choosing LLMs for Strategic Agent Interactions

arXiv:2610.18354v1 Announce Type: new Abstract: Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capabil...

By Arastun Mammadli, Herbert Woisetschl\"ager, Jawad Fayaz, Shiqiang Wang

llms rag agents reinforcement-learning benchmarks safety

arXiv AI

Oct 15

Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents

arXiv:2610.18614v1 Announce Type: new Abstract: Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human....

By Ashutosh Hathidara

llms agents reinforcement-learning

arXiv Machine Learning

Oct 15

MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning

arXiv:2610.19920v1 Announce Type: new Abstract: Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of st...

By Yanyi Su, Chenyan Wang, Yulei Gong, Yeyun Chen, Xiaohui Yang, Jun Cheng

llms agents reinforcement-learning

arXiv AI

Oct 15

A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning

arXiv:2610.14041v1 Announce Type: cross Abstract: Inverse Reinforcement Learning (IRL) is classically solved using Lagrangian optimisation, by jointly optimising a primal-dual problem with gradient d...

By Anish Diwan, Jan Peters, Oleg Arenz

reinforcement-learning

arXiv AI

Oct 15

Reinforcement Learning from Real-Robot Interaction without High-Quality State Estimates

arXiv:2610.14042v1 Announce Type: cross Abstract: A longstanding goal for robot reinforcement learning (RL) is that robots learn from their own physical experience, as humans and animals do. A key ob...

By Ryan Gao, Ashvin Anilkumar, Nicholas Corrado, William Cong, Josiah Hanna

reinforcement-learning robotics

arXiv Machine Learning

Oct 15

Provable Transformer Context Compression for In-Context Reinforcement Learning

arXiv:2610.20004v1 Announce Type: new Abstract: Transformers can perform in-context reinforcement learning without parameter updates. However, existing theoretical constructions often require context...

By Yajie Zhao, Yingjun Mo, Zhiyong Wang, Bo Tang, Chao Xu, Fang Kong

llms reinforcement-learning

arXiv AI

Oct 15

Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval

arXiv:2610.14465v1 Announce Type: cross Abstract: Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on uncon...

By Zhisheng Qi, Haoyu Han, Jiaxi Li, Bing He, Huiyuan Chen, Franck Dernoncourt, Ryan A. Rossi, Mahantesh M. Halappanavar, Jin Lu, Yu Zhang, Tianming Liu, Yu Wang

rag agents reinforcement-learning fine-tuning

arXiv Computation and Language

Oct 15

QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models

arXiv:2601.08689v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong capabilities in finance-oriented question answering, yet their evaluation on professional quantitati...

By Zhaolu Kang, Junhao Gong, Wenqing Hu, Yingjie He, Kehan Jiang, Leqi Zheng, Shuo Yin, Zhicheng Fang, Chunlei Meng, Eric Hanchen Jiang, Yunfei Feng, Yitong Leng, Junfan Zhu, Xiaoyou Chen, Xi Yang, Richeng Xuan

llms nlp reinforcement-learning fine-tuning benchmarks

arXiv AI

Oct 15

Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries

arXiv:2610.06269v2 Announce Type: replace Abstract: Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process...

By Chonghe Jiang, Ao Qu, Siyuan Liu, Ruoyun Ma, Zijian Zhou, Dingyi Zhuang, Bo Liu, Han Zheng, Hanfei Yu, Baichuan Mo, Jinhua Zhao, Paul Pu Liang

llms agents reinforcement-learning benchmarks

arXiv AI

Oct 15

Neos: Learning to Interleave Search and Visual Reasoning

arXiv:2610.17043v1 Announce Type: new Abstract: Recent multimodal deep search agents have advanced tool use and visual content retrieval, yet they still struggle to convert intermediate visual eviden...

By Ekko He, Jack Hong, Shilin Yan, Xintong Zhang, Yujie Zhang, Wenjie Li, Haoran Sun, Kaixun Jiang, Jiyuan Fu, Guannan Zhang, Hongwei Xue

agents reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Oct 15

Size Generalization for Diffusion Routing Solvers

arXiv:2610.17192v1 Announce Type: new Abstract: Routing problems, like the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP), are NP-hard and slow to solve for large...

By Barak Itzchak Davidovitch, Eli Meirom, Ethan Fetaya, Gal Chechik

diffusion reinforcement-learning

arXiv Machine Learning

Oct 15

Adversarial Reinforcement Learning for Robust Planetary Landing

The paper presents a method for improving the robustness of deep reinforcement learning (DRL) policies used in planetary landing by employing adversarial reinforcement learning. A secondary agent generates physically constrained perturbations that challenge the landing controller, creating an asymmetric zero‑sum game. Training is conducted in three stages—baseline learning, stochastic robustness enhancement, and iterative adversarial optimization—showing that adversarial disturbances uncover vulnerabilities missed by conventional randomization and hint at better generalization to unseen perturbations.

By Miguel Leiva-V\'elez, Nicolas Gaston-Rozado, Andrea Scorsoglio, Hodei Urrutxua, V\'ictor Rodr\'iguez-Fern\'andez

agents reinforcement-learning safety

arXiv Machine Learning

Oct 15

TANGO: RNA Topology and Geometry Co-Design

arXiv:2610.20277v1 Announce Type: new Abstract: Designing RNA sequences that satisfy target tertiary-structure objectives is an important problem in RNA engineering, with broad applications in synthe...

By Tianmeng Hu, Biao Luo, Ke Li

agents reinforcement-learning fine-tuning

arXiv AI

Oct 15

PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents

arXiv:2610.14636v1 Announce Type: new Abstract: Terminal rewards make multi-turn agents trainable without step-level annotations, but group-relative advantages provide little guidance about which int...

By Jie Yang, Mianqiu Huang, Yiwei Zhao, Bo Wang, Yang Liu, Yuxin Wang

agents reinforcement-learning

arXiv AI

Oct 15

Equal-information evaluation of credit assignment in modular financial reinforcement learning

arXiv:2610.14750v1 Announce Type: new Abstract: Credit assignment in modular financial reinforcement learning is difficult to evaluate because an attributed signal may improve a component loss withou...

By Gennadiy Chistiakov, Yury Yanovich

reinforcement-learning safety

arXiv AI

Oct 15

Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling

arXiv:2610.14913v1 Announce Type: new Abstract: Reinforcement learning (RL) is essential for adaptive decision-making, e.g., robust Meta-RL and domain randomization (DR), and efficient post-training...

By Jiarong Wen, Qi Tao, Kaiyu Zhang, Yun Qu, Lizhou Cai, Heming Zou, Yuhang Jiang, Qi Wang

llms agents reinforcement-learning safety

arXiv AI

Oct 15

FleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization

arXiv:2610.14970v1 Announce Type: new Abstract: With the rapid evolution of large language models (LLMs), there is an increasing demand for effective personalization techniques that can adapt model b...

By Kounianhua Du, Jianxing Liu, Kangning Zhang, Wenxiang Jiao, Yuan Lu, Jiarui Jin, Jianghao Lin, Weiwen Liu, Yong Yu, Weinan Zhang

llms agents reinforcement-learning efficiency

arXiv AI

Oct 15

Self-Evolving Visual Agent via Margin Reward

arXiv:2610.15084v1 Announce Type: new Abstract: Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool in...

By Wenxi Yang, Yuzhong Zhao, Baochang Zhang, Yunfan Liu, Qixiang Ye

agents reinforcement-learning multimodal benchmarks

Get the daily briefing