Reinforcement learning

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

7,243 stories · RSS feed

arXiv AI

Jun 2

Robust Shielding for Safe Reinforcement Learning

arXiv:2606. 00270v1 Announce Type: new Abstract: Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs).

By Edwin Hamel-De le Court, Thom Badings, Alessandro Abate, Francesco Belardinelli, Francesco Fabiano

agents reinforcement-learning safety

arXiv Machine Learning

Jun 2

Adaptive Time Series Reasoning via Segment Selection

arXiv:2602. 18645v2 Announce Type: replace Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series.

By Shvat Messica, Jiawen Zhang, Kevin Li, Theodoros Tsiligkaridis, Marinka Zitnik

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 2

Emergent Collaborative Deliberation in Multi-Model AI Systems: A BFT-Derived Protocol for Epistemic Synthesis

arXiv:2606. 00005v1 Announce Type: new Abstract: We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model disagreement as epistemic signal rather than error.

By VD Doske

llms reinforcement-learning safety

arXiv Machine Learning

Jun 2

Mean Flow Policy Optimization

arXiv:2604. 14698v2 Announce Type: replace Abstract: Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL).

By Xiaoyi Dong, Xi Sheryl Zhang, Jian Cheng

diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jun 2

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis

arXiv:2510. 09260v2 Announce Type: replace-cross Abstract: Recent work has shown that RLHF is highly susceptible to backdoor attacks.

By Subrat Kishore Dutta, Yuelin Xu, Piyush Pant, Xiao Zhang

llms rag reinforcement-learning

arXiv Machine Learning

Jun 2

OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction

arXiv:2510. 17532v2 Announce Type: replace-cross Abstract: Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinical data.

By Raghu Vamshi Hemadri, Geetha Krishna Guruju, Kristi Topollai, Anna Ewa Choromanska

llms nlp reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 2

ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution

arXiv:2602. 03203v2 Announce Type: replace-cross Abstract: Recently, large language models (LLMs) have shown remarkable reasoning abilities by producing long reasoning traces.

By Zican Dong, Peiyu Liu, Junyi Li, Zhipeng Chen, Han Peng, Shuo Wang, Wayne Xin Zhao

llms reinforcement-learning efficiency benchmarks

arXiv AI

Jun 2

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

arXiv:2603. 09692v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert domains.

By Davit Melikidze, Marian Schneider, Jessica Lam, Martin Wertich, Ido Hakimi, Barna P\'asztor, Andreas Krause

llms reinforcement-learning fine-tuning

arXiv AI

Jun 2

Dynamic Entropy Tuning in Reinforcement Learning Low-Level Quadcopter Control: Stochasticity vs Determinism

arXiv:2512. 18336v2 Announce Type: replace-cross Abstract: This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy.

By Youssef Mahran, Zeyad Gamal, Ayman El-Badawy

reinforcement-learning

arXiv Machine Learning

Jun 2

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning

arXiv:2605. 03403v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models.

By Yujun Li, Hongyuan Zhang, Yuan Yuan

llms reinforcement-learning multimodal benchmarks safety

arXiv Machine Learning

Jun 2

Online Learning in MDPs with Partially Adversarial Transitions and Losses

arXiv:2602. 09474v2 Announce Type: replace Abstract: We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode.

By Ofir Schlisselberg, Tal Lancewicki, Yishay Mansour

reinforcement-learning safety

arXiv AI

Jun 2

Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation

arXiv:2606. 01897v1 Announce Type: new Abstract: Traditional Video Quality Assessment (VQA) focuses narrowly on aesthetic fidelity, overlooking the complex social dynamics that define quality in User-Generated Content (UGC).

By Tianjiao Li, Kai Zhao, Xiang Li, Yang Liu, Huyang Sun

reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv AI

Jun 2

MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition

arXiv:2606. 00708v1 Announce Type: new Abstract: Automated data science is a structured model-selection problem.

By Yifan Bao, Xinyu Xi, Xinyu Liu, Wen Ge, Lei Jiang, Kevin Zhang, Raad Khraishi, Yihao Ang, Anthony K. H. Tung, Lukasz Szpruch, Hao Ni

llms agents reinforcement-learning

arXiv AI

Jun 2

Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification

arXiv:2606. 01160v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used with formal interactive theorem provers such as Lean 4.

By Shihao Ji, Haotao Tan, Zihui Song, Mingyu Li

llms reinforcement-learning safety

arXiv AI

Jun 2

You Can Learn Tokenization End-to-End with Reinforcement Learning

arXiv:2602. 13940v2 Announce Type: replace-cross Abstract: Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end.

By Sam Dauncey, Roger Wattenhofer

llms nlp reinforcement-learning

arXiv Machine Learning

Jun 2

Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms

arXiv:2508. 02812v3 Announce Type: replace Abstract: Causal graphical models can encode large amounts structural knowledge, both from the background knowledge of domain experts and the structural knowledge discovered from randomized experiments or observational data.

By Katherine Avery, Chinmay Pendse, David Jensen

reinforcement-learning

arXiv Machine Learning

Jun 2

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.

By Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters

reinforcement-learning robotics fine-tuning

arXiv AI

Jun 2

BAGEN: Are LLM Agents Budget-Aware?

arXiv:2606. 00198v1 Announce Type: cross Abstract: While agents are increasingly spending more resources, today agent cost is mostly measured only after execution.

By Yuxiang Lin, Zihan Wang, Mengyang Liu, Yuxuan Shan, Longju Bai, Junyao Zhang, Xing Jin, Boshan Chen, Jinyan Su, Xingyao Wang, Jiaxin Pei, Manling Li

llms agents reinforcement-learning fine-tuning

arXiv AI

Jun 2

Control of a Twin Rotor using Twin Delayed Deep Deterministic Policy Gradient (TD3)

arXiv:2512. 13356v2 Announce Type: replace-cross Abstract: This paper proposes a reinforcement learning (RL) framework for controlling and stabilizing the Twin Rotor Aerodynamic System (TRAS) at specific pitch and azimuth angles and tracking a given trajectory.

By Zeyad Gamal, Youssef Mahran, Ayman El-Badawy

agents reinforcement-learning

arXiv AI

Jun 2

CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts

arXiv:2606. 00609v1 Announce Type: cross Abstract: Reinforcement learning (RL) with verifiable rewards has achieved strong progress in reasoning-oriented LLMs, but extending it to multi-domain RL remains challenging due to reward unreliability in non-verifiable tasks and capability interference across domains.

By Rui Zhang, Xinle Wu, Yao Lu

llms reinforcement-learning benchmarks

Get the daily briefing