Reinforcement learning

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

7,243 stories · RSS feed

arXiv AI

Jun 8

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates

arXiv:2601. 18510v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment.

By Yibo Li, Zijie Lin, Ailin Deng, Xuan Zhang, Yufei He, Shuo Ji, Tri Cao, Bryan Hooi

llms agents reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 8

Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning

arXiv:2606. 06673v1 Announce Type: new Abstract: Sparse rewards and heterogeneous task sequences remain persistent challenges in Reinforcement Learning (RL), often resulting in slow convergence, weak generalization, and inefficient exploration.

By Ujjwal Bhatta, Utsabi Dangol, Sumaly Bajracharya, Rodrigue Rizk, KC Santosh

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 8

SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling

arXiv:2606. 06820v1 Announce Type: cross Abstract: Agentic Large Language Model (LLM) systems decompose complex tasks into workflow Directed Acyclic Graphs (DAGs) whose primitives must be scheduled on heterogeneous clusters.

By Zhifei Xu, Jierui Lan, Zixuan Liang, Aiji Liang, Jinxi He

llms agents reinforcement-learning fine-tuning

arXiv AI

Jun 8

Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning

arXiv:2605. 12655v2 Announce Type: replace Abstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives.

By Wo Wei Lin, Ethan Rathbun, Enrico Marchesini, Xiang Zhi Tan

agents reinforcement-learning

arXiv Machine Learning

Jun 8

DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs

arXiv:2505. 23131v2 Announce Type: replace Abstract: We study the problem of assigning operations in a dataflow graph to devices to minimize execution time in a work-conserving system, with emphasis on complex machine learning workloads.

By Xinyu Yao, Daniel Bourgeois, Abhinav Jain, Yuxin Tang, Jiawen Yao, Zhimin Ding, Arlei Silva, Chris Jermaine

reinforcement-learning

arXiv AI

Jun 8

Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards

arXiv:2606. 06825v1 Announce Type: cross Abstract: Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined over a single SQL state.

By Shihao Zhang, Xiaoman Wang, Yuan Liu, Yunshi Lan, Weining Qian

llms reinforcement-learning safety data-engineering

arXiv Machine Learning

Jun 8

Controllable Molecular Generative Foundation Models

arXiv:2605. 15354v2 Announce Type: replace Abstract: Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tasks with reliable controllability.

By Yihan Zhu, Yuhan Liu, Weijiang Li, Tengfei Luo, Meng Jiang

rag diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jun 8

Self-evolving LLM agents with in-distribution Optimization

arXiv:2606. 07367v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge.

By Yudi Zhang, Meng Fang, Zhenfang Chen, Mykola Pechenizkiy

llms agents reinforcement-learning

arXiv Machine Learning

Jun 8

Directed evolution algorithm drives neural prediction

arXiv:2512. 01362v2 Announce Type: replace Abstract: Neural prediction offers a promising approach to forecasting the individual variability of neurocognitive functions and disorders and providing prognostic indicators for personalized invention.

By Yanlin Wang, Nancy M Young, Patrick C M Wong

reinforcement-learning

arXiv Machine Learning

Jun 8

Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies

arXiv:2606. 06555v1 Announce Type: cross Abstract: Noisy evolution strategies under fixed evaluation budgets face a depth-fidelity trade-off: spending evaluations to denoise intra-generation rankings reduces the number of distribution updates the optimizer can execute.

By Sichen Wang, Zhipeng Lu

reinforcement-learning

arXiv AI

Jun 8

StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents

arXiv:2606. 07027v1 Announce Type: new Abstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps.

By Haojie Hao, Longkun Hao, Yihang Lou, Yan Bai, Zhenyang Li, Zhichao Yang, Dongshuo Huang, Hongyu Lin, Lanqing Hong, Jiakai Wang, Xianglong Liu

agents reinforcement-learning

arXiv Machine Learning

Jun 8

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

arXiv:2606. 07006v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior.

By Yongliang Miao, Fengyuan Liu, Wei Shi, Yanguang Liu, Fei Sun, Na Zou, Mengnan Du

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 8

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

arXiv:2605. 17333v2 Announce Type: replace Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual correctness, yet the collective structure of the group output, specifically the distribution of errors, is largely discarded.

By Wenpu Liu, Yuqi Xu, Weichu Xie, Yongfu Zhu, Shuai Dong, Ziyue Wang, Wenqi Shao, Xiaoying Zhang, Tong Yang, Nan Duan, Jiaqi Wang

reinforcement-learning benchmarks

arXiv Machine Learning

Jun 8

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO

arXiv:2606. 06828v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences.

By Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Tianyi Wei, Xiaohang Zhan, Jiaqi Wang, Tong Wu, Xingang Pan, Dahua Lin

llms diffusion reinforcement-learning

arXiv AI

Jun 8

On the Geometry of On-Policy Distillation

arXiv:2606. 07082v1 Announce Type: cross Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood.

By Zhennan Shen, Yanshu Li, Qingyu Yin, Chak Tou Leong, Zhilin Wang, Yanxu Chen, Rongduo Han, Sunbowen Lee, Yi R. Fung

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Jun 8

ViVa: A Video-Generative Value Model for Robot Reinforcement Learning

arXiv:2604. 08168v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due to partial observability and delayed feedback.

By Jindi Lv, Hao Li, Jie Li, Fankun Kong, Yang Wang, Pengfei Yi, Yifei Nie, Xiaofeng Wang, Zheng Zhu, Chaojun Ni, Qiuping Deng, Hengtao Li, Jiancheng Lv, Guan Huang

llms reinforcement-learning robotics multimodal benchmarks

arXiv AI

Jun 8

Agentic Physical AI toward a Domain-Specific Foundation Model for Energy Systems: A Case Study on Nuclear Reactor Control

arXiv:2512. 23292v5 Announce Type: replace Abstract: The prevailing paradigm in AI for physical systems: scaling general-purpose foundation models toward universal multimodal reasoning, confronts a barrier at the control interface.

By Yoon Pyo Lee, Samrendra Roy, Kazuma Kobayashi, Sajedul Talukder, Diab Abueidda, Seid Koric, Souvik Chakraborty, Syed Bahauddin Alam

llms agents reinforcement-learning multimodal safety

arXiv Machine Learning

Jun 8

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling

arXiv:2601. 08097v2 Announce Type: replace-cross Abstract: Reward modeling is essential for aligning large language models with human preferences, yet predominant architectures rely on a static pooling strategy to condense sequences into scalar scores.

By Yongliang Miao, Yangyang Liang, Mengnan Du

llms reinforcement-learning safety

arXiv Machine Learning

Jun 8

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

arXiv:2503. 03660v4 Announce Type: replace Abstract: We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets.

By Dong Tian, Onur Celik, Gerhard Neumann

llms rag reinforcement-learning benchmarks

arXiv AI

Jun 8

MacArena: Benchmarking Computer Use Agents on an Online macOS Environment

arXiv:2606. 06560v1 Announce Type: cross Abstract: Computer-use agents (CUAs) operate graphical user interfaces (GUIs) through vision and control primitives, and their capabilities have advanced rapidly, driven in part by standardized online evaluation benchmarks such as OSWorld, which serve both as evaluation tools and as training environments for reinforcement learning.

By Victor Muryn, Maksym Shamrai, Sofiia Mazepa, Yehor Khodysko

agents reinforcement-learning benchmarks

Get the daily briefing