Reinforcement learning

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

6,740 stories · RSS feed

arXiv AI

Oct 1

ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning

arXiv:2609.39665v1 Announce Type: new Abstract: Embodied agents must determine where to act, anticipate the resulting scene changes, and interpret observed outcomes to guide subsequent actions. This...

By Chenyangguang Zhang, Malgorzata Gwiazda, Guanlong Jiao, Yuanchen Ju, Federico Tombari, Koushil Sreenath, Marc Pollefeys, Sunghwan Hong

llms agents reinforcement-learning robotics fine-tuning multimodal

arXiv AI

Oct 1

ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning

arXiv:2609.38409v1 Announce Type: new Abstract: Recent progress in large language model reasoning has been driven by benchmarks and reinforcement learning environments with automatically verifiable r...

By \.Ibrahim Ethem Deveci, Funda Tan \c{C}al{\i}k, Bar{\i}\c{s} Deniz Sa\u{g}lam, Duygu Ataman

llms reinforcement-learning benchmarks

arXiv AI

Oct 1

Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models

arXiv:2605.07872v2 Announce Type: replace-cross Abstract: Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains s...

By Yuancheng Wei, Linli Yao, Lei Li, Haojie Zhang, Hao Zhou, Fandong Meng, Xu Sun

reinforcement-learning multimodal benchmarks

arXiv AI

Oct 1

Code to Control: Synthesizing Parameterized Reactive Controllers

arXiv:2609.38733v1 Announce Type: new Abstract: Recent LLM-based approaches to control either invoke a language model to select actions or synthesize world models that require planning at every decis...

By Zergham Ahmed, Joshua B. Tenenbaum, Chris Bates, Samuel J. Gershman

llms reinforcement-learning robotics

arXiv AI

Oct 1

Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching

arXiv:2609.38955v1 Announce Type: cross Abstract: Inverse Reinforcement Learning (IRL) aims to recover a reward function that explains expert demonstrations. Existing IRL methods typically rely on a...

By Yang chen, Yitan Zhang, Michael Witbrock, Shuyue Hu

diffusion reinforcement-learning benchmarks

arXiv AI

Oct 1

Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation

arXiv:2609.38282v1 Announce Type: new Abstract: Vision-language models may rewrite anomalous text in images into linguistically plausible expressions, compromising OCR transcription faithfulness. Seq...

By Baode Wang, Zuming Huang, Kexuan Ren, Jun Huang, Wei Chu

llms computer-vision reinforcement-learning efficiency multimodal

arXiv AI

Oct 1

MoFlow: Multi-Objective Agentic Workflow Generation

arXiv:2609.38294v1 Announce Type: new Abstract: We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. E...

By Yining Lu, Aurelie Lozano, Xi Yang, Naoki Abe, Yu Deng, Meng Jiang

agents nlp reinforcement-learning benchmarks

arXiv AI

Oct 1

OpenJev-RLCD: A Working RLCD Implementation

arXiv:2609.38850v1 Announce Type: new Abstract: Decision models such as Jev answer questions with probabilities, which are only useful if they are calibrated. Open-source reproductions rely on superv...

By Zhimin Gao, Pichao Wang

reinforcement-learning fine-tuning

arXiv AI

Oct 1

Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation

arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...

By Zhihan Zhang, Lizi Liao

llms reinforcement-learning multimodal benchmarks

arXiv AI

Oct 1

EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning

arXiv:2609.39371v1 Announce Type: new Abstract: In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements refe...

By Yitong Qiao, Yancheng Jin, Lei Liu, Yue Shen, Jian Wang, Jinjie Gu, Zhixuan Chu

llms agents reinforcement-learning fine-tuning benchmarks data-engineering

arXiv AI

Oct 1

Unlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVR

arXiv:2609.40115v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an important approach for improving reasoning during post-training. Recent work sugges...

By Chandak Chakma, Syed Nazmus Sakib, Nafiul Haque, Shifat E. Arman

reinforcement-learning

arXiv AI

Oct 1

Searching for BSM Experimental Signatures with Large Lagrangian Models

arXiv:2609.38309v1 Announce Type: cross Abstract: The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminatin...

By Ibrahim Elsharkawy, Victoria Knapp-Perez, Wahid Bhimji, Aishik Ghosh

llms agents reinforcement-learning fine-tuning

arXiv AI

Oct 1

From Search to Signal: Online Post-Training in Automatic Heuristic Design

arXiv:2609.39383v1 Announce Type: cross Abstract: Large language model (LLM)-based automatic heuristic design (AHD) iteratively proposes and refines heuristics, pairing design rationales with executa...

By Yilun Yuan, Tianyu Zhou, Zhenzhou Tang

llms reinforcement-learning

arXiv AI

Oct 1

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

arXiv:2609.40195v1 Announce Type: cross Abstract: Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spann...

By Guangzhi Xiong, Xinyuan Zhang, Xiao Yang, Hyokun Yun, Kai Zhang, Shiun-Zu Kuo, Hyeonjeong Ha, Xilun Chen, Kai Sun, Lucas Liang, Guangqiang Dong, Ejaz Ahmed, Ahmed A Aly, Anuj Kumar, Raffay Hamid, Aidong Zhang, Xin Luna Dong

agents reinforcement-learning multimodal benchmarks

arXiv AI

Oct 1

From Compound Figures to Medical Multi-image Reasoning: Scaling Multimodal Large Language Models with Biomedical Literature

arXiv:2511.22232v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly capable in medical imaging, yet most focus on single-image settings. Clinical inter...

By Zhen Chen, Yihang Fu, Rong Zhou, Serina Applebaum, Min Kyu Kim, Aidan Gilson, Morten Lee, Salahudeen Mirza, Gabriel Madera, Mauro Giuffre, Yuanting Pan, Roy Jiang, Hyunjae Kim, Hua Xu, Qingyu Chen

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Oct 1

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

arXiv:2604.09531v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition, largely be...

By Guanyu Zhou, Yida Yin, Wenhao Chai, Shengbang Tong, Xingyu Fu, Zhuang Liu

llms diffusion reinforcement-learning fine-tuning multimodal benchmarks

arXiv Computation and Language

Oct 1

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift

arXiv:2605.25629v3 Announce Type: replace Abstract: Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched tra...

By Khoi Le, Tri Cao, Phong Nguyen, Cong-Duy Nguyen, Anh Tuan Luu, Miao Chunyan, See-Kiong Ng, Thong Nguyen

reinforcement-learning fine-tuning

arXiv Computer Vision

Oct 1

ReDiF: Resource-Efficient Few-Step Diffusion Distillation via Reinforcement Learning

arXiv:2512.22802v2 Announce Type: replace-cross Abstract: Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remai...

By Amirhossein Tighkhorshid, Zahra Dehghanian, Hamid R. Rabiee

diffusion reinforcement-learning efficiency safety

arXiv AI

Oct 1

Learning to Route in Visual Space via Multi-Step Embedding Retrieval

The paper introduces VHOP, a data generation framework and benchmark for visual agentic search, and VHOP-Router, an end‑to‑end training pipeline that turns a standard embedding model into an autoregressive multi‑step retriever operating directly in visual latent space. VHOP-Router eliminates the need for intermediate text queries, boosting retrieval accuracy from under 5% to 76.3% and improving task success rates by 52.7% while dramatically reducing token usage and API payloads. The approach generalizes to unseen difficulty levels and realistic test sets, offering an efficient solution that preserves native LLM capabilities.

By Tianyu Chen, Mingyuan Zhou, Jiaxing Wu

llms rag agents diffusion reinforcement-learning fine-tuning benchmarks

arXiv Computation and Language

Oct 1

CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL

arXiv:2609.39533v1 Announce Type: new Abstract: During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high r...

By Shouli Wang, Yanfeng Jia, Zhihao Ou, Zitao Su, Ruize He, Haotong Xie, Hao Peng, Juanzi Li, Xiaozhi Wang

llms reinforcement-learning fine-tuning safety

Get the daily briefing