Reinforcement learning

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

7,242 stories · RSS feed

arXiv AI

Jun 24

ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning

arXiv:2606. 24601v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) addresses the problem of training multiple agents that pursue collaborative, competitive, or mixed objectives.

By Anurag Akula, Satheesh K. Perepu, Abhishek Sarkar, Kaushik Dey

rag agents reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jun 24

Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation

arXiv:2606. 24515v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) execute high-level user goals by perceiving and acting directly within graphical user interfaces.

By Marta Sumyk, Oleksandr Kosovan

llms agents reinforcement-learning fine-tuning multimodal

arXiv Machine Learning

Jun 24

A Robust Model-Based Approach for Continuous-Time Policy Evaluation with Unknown L\'evy Process Dynamics

arXiv:2504. 01482v3 Announce Type: replace-cross Abstract: This paper develops a model-based framework for continuous-time policy evaluation (CTPE) in reinforcement learning, incorporating both Brownian and L\'evy noise to model stochastic dynamics influenced by rare and extreme events.

By Qihao Ye, Xiaochuan Tian, Yuhua Zhu

reinforcement-learning

arXiv Machine Learning

Jun 24

AsyncOPD: How Stale Can On-Policy Distillation Be?

arXiv:2606. 24143v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training.

By Wonjun Kang, Kevin Galim, Seunghyuk Oh, Minjun Kang, Sanghyun Park, Donghoon Kim, Minjae Lee, Minseo Kim, Rishabh Tiwari, Yuchen Zeng, Hyung Il Koo, Kangwook Lee

llms reinforcement-learning efficiency safety

arXiv Machine Learning

Jun 24

Sakana Fugu Technical Report

arXiv:2606. 21228v2 Announce Type: replace Abstract: The capabilities of frontier Large Language Models (LLMs) continue to advance, with different providers increasingly specializing in distinct domains.

By Yujin Tang, Edoardo Cetin, Jinglue Xu, Qi Sun, Stefan Nielsen, Vincent Richard, Haruto Goda, Iaroslav Tymchenko, Nhan Nguyen, Hyunin Lee, Mari Ashiga, Shashank Kotyan, So Kuroki, Tarin Clanuwat

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 24

Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization

arXiv:2605. 01482v3 Announce Type: replace Abstract: Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains.

By Yunhan Bu, Quan Zhang, Huaping Zhang, Guotong Geng, Chunxiao Gao, Askar Hamdulla, Juan Wang, Qiuchi Li, Baohua Zhang, Shuai Lei, Yunbo Cao, Zhunchen Luo

llms reinforcement-learning safety

arXiv AI

Jun 24

Grounded Chess Reasoning in Language Models via Master Distillation

arXiv:2603. 20510v2 Announce Type: replace Abstract: Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel.

By Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert, Yahya Elgabra, Blair Yang, Honghua Dong, Ashton Anderson

llms reinforcement-learning fine-tuning efficiency

arXiv Machine Learning

Jun 24

Debate2Create: Robot Co-design via Multi-Agent LLM Debate

arXiv:2510. 25850v3 Announce Type: replace-cross Abstract: We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in physics-based evaluation.

By Kevin Qiu, Marek Cygan

llms agents reinforcement-learning robotics benchmarks

arXiv Machine Learning

Jun 24

Reinforcement Learning to Disentangle Multiqubit Quantum States from Partial Observations

arXiv:2406. 07884v3 Announce Type: replace-cross Abstract: Using partial knowledge of a quantum state to control multiqubit entanglement is a largely unexplored paradigm in the emerging field of quantum interactive dynamics with the potential to address outstanding challenges in quantum state preparation and compression, quantum control, and quantum complexity.

By Pavel Tashev, Stefan Petrov, Matthew T. Diaz, Friederike Metz, Alaina M. Green, Norbert M. Linke, Marin Bukov

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 24

NoContactNoWorries: Estimating Contact through Vision and Proprioception for In-Hand Dexterous Manipulation

arXiv:2606. 24450v1 Announce Type: cross Abstract: Perceiving physical contact is fundamental to dexterous manipulation.

By Soham Patil, Avirup Das, Sourabh Bhosale, Spandan Roy

llms agents reinforcement-learning robotics multimodal

arXiv AI

Jun 24

CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

arXiv:2606. 24636v1 Announce Type: new Abstract: Cinematographic captioning aims to describe how a video is filmed using professional film-language concepts such as camera movement, shot size, depth of field, composition, and shooting angle.

By Xinyu Mao, Yuhui Zeng, Xiaokun Liu, Wenyu Qin, Meng Wang, Xin Tao, Pengfei Wan, Xiaohan Xing, Max Meng

llms diffusion reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 24

Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation

arXiv:2606. 24042v1 Announce Type: new Abstract: Recommender systems often induce filter bubbles and semantic homogenization by monolithically optimizing for immediate user engagement.

By Cl\'audio L\'ucio Do Val Lopes, Lucca Machado da Silva, Andr\'e de Oliveira Brand\~ao

rag agents reinforcement-learning safety

arXiv Machine Learning

Jun 24

Aligning Audio Captions with Human Preferences

arXiv:2509. 14659v3 Announce Type: replace-cross Abstract: Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios.

By Kartik Hegde, Rehana Mahfuz, Yinyi Guo, Erik Visser

reinforcement-learning fine-tuning safety

arXiv AI

Jun 24

Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback

arXiv:2606. 24622v1 Announce Type: new Abstract: Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors.

By Andreas Chouliaras, Luke Connolly, Dimitris Chatzpoulos

reinforcement-learning safety

arXiv AI

Jun 24

LaGO: Latent Action Guidance for Online Reinforcement Learning

arXiv:2606. 24669v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direct controllers, which requires precise action generation and can be unreliable in practice.

By Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong Wu

llms reinforcement-learning robotics benchmarks

arXiv AI

Jun 24

On the Position Bias of On-Policy Distillation

arXiv:2606. 22600v2 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers.

By Yan Xie, Sijie Zhu, Tiansheng Wen, Bo Chen, Yifei Wang

reinforcement-learning efficiency safety

arXiv AI

Jun 24

An Introduction to Causal Reinforcement Learning

arXiv:2606. 24160v1 Announce Type: new Abstract: Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.

By Elias Bareinboim, Junzhe Zhang, Sanghack Lee

agents reinforcement-learning

arXiv AI

Jun 24

Navigating User Behavior toward Personalized Multimodal Generation

arXiv:2606. 24196v1 Announce Type: new Abstract: Modern AIGC pipelines deliver high-fidelity images and videos but presuppose a well-formed creation instruction, while end users rarely articulate visual details, leaving generators misaligned with user demand.

By Hengji Zhou, Yufeng Liu, Ye Liu, Yong Xu, Lianghao Xia, Liqiang Nie

diffusion reinforcement-learning fine-tuning multimodal

arXiv AI

Jun 24

Impatient Bandits: Optimizing for the Long-Term Without Delay

arXiv:2501. 07761v2 Announce Type: replace-cross Abstract: Increasingly, recommender systems are tasked with improving users' long-term satisfaction.

By Kelly W. Zhang, Thomas Baldwin-McDonald, Kamil Ciosek, Lucas Maystre, Daniel Russo

reinforcement-learning

arXiv AI

Jun 24

Towards Spec Learning: Inference-Time Alignment from Preference Pairs

arXiv:2606. 24004v1 Announce Type: cross Abstract: Steering a large language model (LLM) toward a desired behavior typically relies on an iterative process of hand-crafting a prompt based on a careful inspection of the model's responses.

By Dhriti Krishnan, Tejas Goyal, Jaromir Savelka

llms reinforcement-learning fine-tuning safety

Get the daily briefing