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

Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play

arXiv:2610.15449v2 Announce Type: new Abstract: Despite significant advances in language understanding, Large Language Models (LLMs) can still miss meaning hidden in plain sight, failing to identify...

By Yisong Xiao, Benlei Cui, Haiwen Hong, Shiji Zhao, Zonghao Ying, Yaoyuan Zhang, Longtao Huang, Aishan Liu, Hui Xue, Ting Ma, Xianglong Liu

llms reinforcement-learning safety

arXiv AI

Oct 15

ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation

arXiv:2610.15956v1 Announce Type: new Abstract: Vision-language-action models for embodied navigation typically rely on RGB observations, limiting their applicability in lights-out industrial environ...

By Wenjun Huang, Shenghao Fu, Yian Jin, Yang Ni, Yifan Li, Lichi Li, Xingjian Diao, Pengfei Zhang, Yutong Song, Hanning Chen, Jiarui Cui, Tianyu Yang, Shilong Li, Yu Kong, Mohsen Imani

reinforcement-learning robotics multimodal benchmarks

arXiv AI

Oct 15

EPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design

arXiv:2610.17379v1 Announce Type: new Abstract: LLM-based automated heuristic design (AHD) discovers heuristics for combinatorial optimization problems (COPs), where an LLM generates candidates in an...

By Oguzhan Gungordu, Ayse Tursucular, Siheng Xiong, Faramarz Fekri

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Oct 15

Learning to Play: Reinforcement Learning and Games

arXiv:2610.17391v1 Announce Type: new Abstract: Amazing breakthroughs in reinforcement learning have taken place. Computers teach themselves to play Chess and Go and beat world champions. There is ta...

By Aske Plaat

reinforcement-learning

arXiv AI

Oct 15

Beyond the Verdict: Agentic Code Judging with Verifiable Feedback

arXiv:2610.18760v1 Announce Type: new Abstract: Test-time scaling for large language models (LLMs) can involve generating multiple candidate solutions for selection or revising an earlier attempt. To...

By Zheye Deng, Sha Li, Changlong Yu, Xin Liu, Qin Lu, Priyanka Nigam, Yangqiu Song

llms agents reinforcement-learning

arXiv AI

Oct 15

Showing versus Doing: Teaching by Demonstration

arXiv:2610.14004v1 Announce Type: cross Abstract: People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contr...

By Mark K. Ho, Michael L. Littman, James MacGlashan, Fiery Cushman, Joseph L. Austerweil

reinforcement-learning

arXiv AI

Oct 15

Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine

arXiv:2610.14705v1 Announce Type: cross Abstract: Large language models have advanced medical reasoning, but clinically grounded reasoning in traditional Chinese medicine (TCM) remains challenging be...

By Rui Hua, Yu Wei, Ziri Jin, Zhuo Sun, Kai Chang, Jianan Xia, Zixin Shu, Xiaodong Li, Dongmei Jia, Fei Dong, Runshun Zhang, Jian Yu, Hao Xu, Haibin Yu, Jiansheng Li, Baoyan Liu, Wenjia Wang, Xuezhong Zhou

llms reinforcement-learning benchmarks safety

arXiv AI

Oct 15

Integrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient

arXiv:2610.14723v1 Announce Type: cross Abstract: A method integrating policy gradient with fuzzy inference has been proposed. This method, hereafter referred to as the base model, has high flexibili...

By Seiji Ishihara

diffusion reinforcement-learning safety

arXiv AI

Oct 15

A Sovereign, Indic-First, Reasoning Model

arXiv:2610.15371v1 Announce Type: cross Abstract: Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in Eng...

By Sutanshu Saksena Raj, Prasanjith Pasunuti, Parijat Chatterjee, Daksh Maan, Purusharth Malik, Nayanjit Sarkar, Avinash Benki

llms rag agents nlp reinforcement-learning efficiency benchmarks

arXiv AI

Oct 15

Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction

arXiv:2610.15864v1 Announce Type: cross Abstract: Large-scale personalization is shifting from embedding-table retrieval to LLM-based recommenders that generate the Semantic ID (SID) of the item to r...

By Sejoon Oh, Fernando Amat Gil, Evan Smothers, Dan Iter, Mark Thornburg, Dawit Mureja Argaw, Sourabh Medapati, Thea Wang, Ria Verma, Qiuling Xu, Harshit Syal, Ehsan Gholami, Moumita Bhattacharya, Ashish Rastogi

llms rag reinforcement-learning efficiency

arXiv AI

Oct 15

LLM Value Functions for Credit Assignment in Agentic RL

arXiv:2610.15840v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assign...

By Kaijie Zhu, Weixiang Yan, Omar Attia, Abbas Kazerouni, Alexander Toshev, Andrew Szot

llms agents reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Oct 15

Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards

arXiv:2610.15888v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards spends much of its rollout budget on states that yield no learning signal. We recast this as a questio...

By Yibo Wang, Yuanxin Liu, Zhaoran Wang

agents reinforcement-learning benchmarks

arXiv AI

Oct 15

Growing and Transferring Pathways for LLM Reinforcement Learning

arXiv:2610.16489v1 Announce Type: cross Abstract: Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires con...

By Haolin Tian, Yikang Li, Tonghan Wang

llms reinforcement-learning

arXiv AI

Oct 15

The belief-action gap in language model agents

arXiv:2610.17444v1 Announce Type: cross Abstract: Language model (LM) agents can fail for different reasons, requiring different explanations and interventions. We study how state beliefs, action val...

By Ayse Sila Okcu, Weisheng Wang, Tongmeng Xie, Niall Dalton, Angelos Nalmpantis, Raghu Arghal, Mario Giulianelli

llms agents reinforcement-learning

arXiv AI

Oct 15

Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning

arXiv:2610.17456v1 Announce Type: cross Abstract: Language models are often evaluated alone but increasingly deployed together, routed between, made to debate, ensembled, or collaboratively trained....

By Shangbin Feng, Yulia Tsvetkov, Jan Kautz, David Acuna

llms reinforcement-learning benchmarks

arXiv AI

Oct 15

PrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning

arXiv:2610.17667v1 Announce Type: cross Abstract: Diffusion models and Flow Matching can represent flexible distributions over robot actions, but many reinforcement learning algorithms also require t...

By Congzhong Sun, Ning Tan

llms diffusion reinforcement-learning robotics multimodal

arXiv AI

Oct 15

RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning

arXiv:2610.17623v2 Announce Type: cross Abstract: Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the...

By Kunwang Zheng, Xinyu Sun, Yu Cao, Shuocheng Li, Lei Cheng, Ying Liu, Qilong Zhang, Jinlong Chen, Hua Yang, Qianglong Chen

reinforcement-learning efficiency

arXiv AI

Oct 15

From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning

arXiv:2610.18057v1 Announce Type: cross Abstract: Transformers can implement reinforcement-learning algorithms in context, yet how off-policy control emerges within Transformers remains poorly unders...

By Yingjun Mo, Yajie Zhao, Fang Kong

llms reinforcement-learning

arXiv AI

Oct 15

APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation

arXiv:2610.18097v1 Announce Type: cross Abstract: Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed traini...

By Sirui Zhang, Fangyun Wei, Dong Chen, Jinjing Zhao, Yitong Wang, Yunuo Chen, Baining Guo, Zheng-Jun Zha

agents diffusion reinforcement-learning benchmarks

arXiv AI

Oct 15

Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

arXiv:2610.18356v1 Announce Type: cross Abstract: City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large o...

By Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li

agents reinforcement-learning multimodal

Get the daily briefing