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

Ember: A Kilobyte-State Optimizer for Token Interfaces

arXiv:2607.01455v4 Announce Type: replace-cross Abstract: Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface betw...

By Kathan Shah

llms rag reinforcement-learning fine-tuning

arXiv AI

Oct 15

PTGPO: Prefix Tree Group Policy Optimization

arXiv:2610.14737v1 Announce Type: cross Abstract: Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediat...

By Ruolin Chen, Yang Li, Jihang Wang, Zhuoya Zhao, Yuchen Liu, Jiaming Xu, Qian Zhang

agents reinforcement-learning benchmarks

arXiv AI

Oct 15

DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter

arXiv:2610.17666v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps....

By Xuyan Ye, Xiyan Fu, Shengda Fan, Jiawei Cui, Yankai Lin, Wei Lu

llms agents reinforcement-learning

arXiv AI

Oct 15

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

arXiv:2610.17552v1 Announce Type: cross Abstract: Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference r...

By Ruchang Yao, Shi Guo, Junhao Zhuang, Mingde Yao, Xin Cai, Jiahao Zhan, Bin Fu, Xinyuan Chen, Yu Qiao, Tianfan Xue

diffusion reinforcement-learning efficiency

arXiv AI

Oct 15

Vela: User Behavior as Supervision Sparks LLM Intelligence

arXiv:2610.14709v1 Announce Type: cross Abstract: Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommen...

By Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Weiqiang Hang, Luqing Wang, Zejian Wang, Zirui Tu, Jingsheng Mao, Shaobo Hu, Yang Luo, Jiale Guo, Jin Zhang, Yudan Liu, Zhaokai Luo, Ren Huan, Yao Hu, Chengyue Jiang, Wenjie Li, Chuan Mu

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Oct 15

IsoVRBench: Video Reward Modeling Without Human Feedback

arXiv:2610.17234v1 Announce Type: new Abstract: Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignme...

By Shuyue Stella Li, Jacqueline He, Jiahui Chen, Sreya Dutta Roy, Yulia Tsvetkov, Luke Zettlemoyer, Marjan Ghazvininejad, Xiaochuang Han

diffusion reinforcement-learning benchmarks safety

arXiv AI

Oct 15

Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation

arXiv:2610.16224v1 Announce Type: cross Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challen...

By Zixu Wang, Xiaoran Zhao, Yahui Liu, Feng-ao Wang, Junhao Xiao, You Shu, Bing Liu, Yiting Liu, Songlei Jian, Zhiliang Tian, Dongsheng Li

agents diffusion reinforcement-learning fine-tuning benchmarks

arXiv AI

Oct 15

A Survey of Flow Matching in Reinforcement Learning

arXiv:2610.16275v1 Announce Type: cross Abstract: Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling express...

By Nabuat Zaman Nahim, Fairoz Nower Khan, Peizhong Ju

diffusion reinforcement-learning fine-tuning efficiency multimodal safety

arXiv AI

Oct 15

Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards

arXiv:2610.17893v1 Announce Type: new Abstract: Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing informati...

By Keru Chen, Sen Lin, Yingbin Liang, Nathaniel D. Bastian, Shaofeng Zou

llms agents reinforcement-learning

arXiv AI

Oct 15

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

arXiv:2610.18860v1 Announce Type: new Abstract: Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable,...

By Xin Gao, Yifan Yang, Xin Li, Pan Wang, Yan Li, Muzhao Tian, Mingxi Cheng, Bei Liu, Kai Qiu, Qi Dai, Dong Chen, Yue Dong, Leandros Tassiulas, Rex Ying, Ji Li, Chong Luo

llms reinforcement-learning multimodal benchmarks

arXiv AI

Oct 15

PreSO: Privileged Representation Isolation for On-Policy Self-Distillation

arXiv:2610.14001v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learn...

By Yuhang Yang, Mingxuan Xia, Chao Ye, Shuai Zhu, Shouqing Yang, Haobo Wang, Shenzhi Yang, Zhengqing Zang, Chenglong Wang

reinforcement-learning efficiency benchmarks

arXiv AI

Oct 15

PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards

arXiv:2610.18755v1 Announce Type: cross Abstract: Reinforcement learning (RL) from unit tests is the common recipe for post-training code models, but a unit test only asks whether the final program p...

By Yunkai Zhan, Miaosen Chai, Shangshang Wang, Jike Zhong, Yuqing Yang, Deqing Fu, Serina Chang, Wang Bill Zhu

llms reinforcement-learning

arXiv AI

Oct 15

SearchMaster: Grounded and Regulated Self-Play for Search Agents

arXiv:2608.01822v2 Announce Type: replace Abstract: Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search...

By Wentao Tan, Qiong Cao, Jiaqi Wang, Nan Duan

llms agents reinforcement-learning benchmarks

arXiv AI

Oct 15

A Generalist Hanabi Agent

arXiv:2503.14555v2 Announce Type: replace-cross Abstract: Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, thes...

By Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond, Miao Liu, Janarthanan Rajendran, Sarath Chandar

agents reinforcement-learning benchmarks

arXiv AI

Oct 15

Process Rewards for Outcome-Guided Reasoning Steps in LLM Reinforcement Learning

arXiv:2604.02341v2 Announce Type: replace-cross Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final...

By Mohammad Rezaei, Jens Lehmann, Sahar Vahdati

llms reinforcement-learning safety

arXiv Machine Learning

Oct 15

Outcome-Routed Distillation and Reinforcement Learning for Diffusion Language Models

arXiv:2610.19271v1 Announce Type: new Abstract: On-policy distillation provides dense supervision on the student's own samples, but its targets still come from the teacher. Verifier reinforcement lea...

By Wentao Lu, Tianyu Zhu, Jesse Clark

llms diffusion reinforcement-learning efficiency

arXiv Machine Learning

Oct 15

Efficient contextual partial monitoring with general function approximation

arXiv:2610.19804v1 Announce Type: new Abstract: We study finite stochastic partial monitoring (PM) games with side information, a paradigm of sequential learning with partial feedback. On each round...

By Kapilan Balagopalan, Hao Qin, Kwang-Sung Jun, Chicheng Zhang

llms reinforcement-learning

arXiv Machine Learning

Oct 15

Non-asymptotic Convergence of Average-reward Q-learning with Options

arXiv:2610.20347v1 Announce Type: new Abstract: We study the finite-sample convergence of Q-learning algorithms for the average-reward formulation of Reinforcement Learning (RL) with options. While o...

By Kintan Saha, Ahana Deb, Anders Jonsson, Debabrota Basu

reinforcement-learning

arXiv Machine Learning

Oct 15

Context Value Informed In-Context Reinforcement Learning

arXiv:2509.23209v2 Announce Type: replace Abstract: In-context reinforcement learning (ICRL) has emerged as an effective paradigm for test time adaptation to unseen tasks without parameter updates. H...

By Wenhao Zhang, Shao Zhang, Xihuai Wang, Yang Li, Ying Wen

reinforcement-learning

arXiv Machine Learning

Oct 15

Maximum-Entropy Exploration with Future State-Action Visitation Measures

arXiv:2603.18965v2 Announce Type: replace Abstract: Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by pr...

By Adrien Bolland, Gaspard Lambrechts, Damien Ernst

agents reinforcement-learning benchmarks

Get the daily briefing