← Back to all news

Reinforcement learning

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

6,856 stories · RSS feed

arXiv Computer Vision
Sep 22

VideoGen-Agent: Reinforcing Video Generation Agents

VideoGen-Agent is a multimodal agent that uses multitask agentic reinforcement learning to coordinate external tools for video generation. It learns to augment, generate, and verify videos through multi‑turn interactions, guided by prompts and intermediate observations. On the new VABench benchmark, the agent improves base text‑to‑video performance by 19.1 points, and further upgrades to generation tools raise the score to 86.1, with human raters favoring the upgraded configuration in 84.3% of comparisons.

By Binxu Li, Haoyi Duan, Yuhui Zhang, Yaohui Zhang, Zihao Lin, Kaituo Feng, Suozhi Huang, Xiangyi Li, Yu Li, Chunyuan Li, Shilong Liu, Mengdi Wang
agentsdiffusionreinforcement-learningfine-tuningmultimodalbenchmarks
More like this →
arXiv Machine Learning
Sep 22

GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training

The paper investigates how post‑training modifies the weights of Large Language Models relative to their pretrained state. By expressing weight updates in the pretrained matrix’s singular value decomposition, the authors separate changes into three geometric components: diagonal (reshaping singular values), off‑diagonal (rotating input‑output coupling), and null‑space (routing outside the original SVD core). Experiments on a math evaluation suite show that removing the diagonal component largely preserves post‑training gains, indicating that improvements stem mainly from reconfiguring and extending pretrained pathways rather than altering singular values.

By Jianing Qi, Hao Tang, Zhigang Zhu
llmsreinforcement-learningfine-tuning
More like this →
arXiv Machine Learning
Sep 22

OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games

OpenBlock is an open, adaptive tile‑matching platform that uses a dual‑track content‑generation system: a deterministic rule‑based generator and an optional learned generator, both verified to ensure every piece set is fully placeable. A self‑play reinforcement‑learning agent diagnoses that long‑bar pieces become largely unplaceable at high board fill, indicating board‑state degeneration rather than difficulty drives late‑game failure. In live play, the learned track improves day‑1 retention by 1.8 percentage points and session duration by 7% compared to the rule track alone.

By Jiang Jun
agentsreinforcement-learning
More like this →
arXiv Machine Learning
Sep 22

RS-Claw-Evolution: Environment-Feedback-Driven Evolution for Lightweight Remote Sensing Agents in Long-Horizon Tasks

RS-Claw-Evolution is an environment-feedback-driven framework designed to enhance lightweight remote sensing agents for long-horizon tasks. It improves agents through three stages—interaction evolution, experience evolution, and decision evolution—using executable code, failure-aware trajectory generation, and reinforcement learning with multi-dimensional rewards. On Earth-Bench, a Qwen3-4B agent trained with this framework reaches 65.9% accuracy, surpassing larger baselines and approaching GPT-5 performance.

By Kai Ouyang, Dongyang Hou, Liangtian Liu, Zeyuan Wang, Ziyu Li, Chengfu Liu, Zichao Tang, Xuezhi Cui, Shengwu Ouyang, Wentao Yang, Hanwen Yu, Haifeng Li
llmsagentsreinforcement-learning
More like this →
arXiv Machine Learning
Sep 22

Autonomous Model Lifecycle Management for Digital Twin-Based Manufacturing Control

The paper introduces a closed‑loop cyber‑physical system for autonomous model lifecycle management in automotive manufacturing, deployed since 2023. It manages paired physics and reinforcement‑learning models, selecting the best candidate through competitive retraining cycles and a Conductor orchestrator that handles plant‑wide inventories and fallback controls. The system incorporates an operator‑trust gate that rejects 23% of policies that deviate from established practice, achieving 28‑45% process stability improvements with no safety incidents.

By Zhengyang (Cissy), Gu, Thomas Cook, Fredaljohn Rohrbaugh, Joseph E. Hernandez, Chris Couch
agentsreinforcement-learningsafety
More like this →
arXiv Machine Learning
Sep 22

The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions

The paper introduces an evidence ladder for evaluating reinforcement learning (RL) in healthcare, outlining stages from problem formulation to lifecycle monitoring. It argues that success in historical data does not guarantee real‑world improvement and highlights assumptions and failure modes at each rung. The authors propose reporting practices to support cumulative evaluation and emphasize that RL should be tested as an intervention within a dynamic sociotechnical system.

By Yunfan Zhao
reinforcement-learning
More like this →
arXiv Machine Learning
Sep 22

Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use

arXiv:2609.24985v1 Announce Type: new Abstract: Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When...

By Zixiang Chen, Wenting Zhao, Zhepeng Cen, Akshara Prabhakar, Jielin Qiu, Jianguo Zhang, Zhiwei Liu, Tulika Manoj Awalgaonkar, Liangwei Yang, Shelby Heinecke, Silvio Savarese, Huan Wang
agentsreinforcement-learningbenchmarks
More like this →
arXiv Machine Learning
Sep 22

EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy

arXiv:2609.22223v1 Announce Type: cross Abstract: Long-form factuality verification is commonly implemented as a static decompose-search-verify pipeline, with separately prompted modules processing c...

By Kening Zheng, Aoying Zheng, Zhigang Chang, Yazhi Guo, Miaotian Guo, Qingwei Zong, Xianhai Xie, Weiqiang Jin, Chengze Li, Hanrong Zhang, Jie Yang, Wei-Chieh Huang, Lingzhe Zhang, Liancheng Fang, Xin Zou, Hanqian Li, Jiahao Huo, Yibo Yan, Zizhuang Deng, Lei Miao, Wei Guo, Haihong Tang, Bo Zheng, Philip S. Yu
llmsagentsreinforcement-learningbenchmarkssafety
More like this →