Reinforcement learning

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

3,495 stories · RSS feed

arXiv AI

Jul 29

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

arXiv:2607. 25659v1 Announce Type: new Abstract: Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria.

By Bo-Wen Zhang, Junwei He, Wen Wang, Song-Lin Lv, Wentao Ma, Rongyi Lin, Shuhan Zhong, Lan-Zhe Guo

llms reinforcement-learning

arXiv AI

Jul 29

Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm

arXiv:2607. 25446v1 Announce Type: new Abstract: Multi-agent frameworks built on large language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which algorithm fuses their work (collaboration protocol).

By Huan Chen, Xiang Song, Jian Jin, Pan Ren, Liang-Jie Zhang

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 29

A Control System, a Dataset, and a Recipe for Making Frozen LLM Agents Learn a Domain

arXiv:2607. 25415v1 Announce Type: new Abstract: Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a planning strategy, and a verification policy.

By Debjyoti Paul

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 29

Pictura: Perspective-View Self-Play at Scale for Driving

arXiv:2607. 26005v1 Announce Type: cross Abstract: Self-play in simulation produces robust driving policies at scale.

By Yuan Yin, Elias Ramzi, Marc Lafon, Valentin Charraut, Victor Bares, Yihong Xu, \'Eloi Zablocki, Alexandre Boulch, Thibault Buhet, Andrei Bursuc, Matthieu Cord

agents reinforcement-learning

arXiv AI

Jul 29

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT

arXiv:2607. 25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves.

By Cen Lu, Yung-Chen Tang, Andrea Cavallaro

reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 29

dtControl2+$\varepsilon$: Trading Optimality for Explainability in MDPs via Decision Trees

arXiv:2607. 25925v1 Announce Type: new Abstract: Over the past decade, decision trees have been used to represent controllers (a.

By Tereza Kinsk\'a, Jan K\v{r}et\'insk\'y, Tobias Meggendorfer, Sabine Rieder, Maximilian Weininger

reinforcement-learning benchmarks

arXiv AI

Jul 29

AdaKP: Online Adaptive Knowledge-Point Selection for Reasoning-Oriented Reinforcement Learning

arXiv:2607. 24833v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is a powerful paradigm for eliciting reasoning in large language models, yet it suffers from severe reward sparsity on competition-level mathematics.

By Zibin Meng, Zhenyu Zhao, Chunqiang Run

llms reinforcement-learning efficiency benchmarks safety

arXiv AI

Jul 29

Structure-aware Relative Policy Optimization for Ranking

arXiv:2607. 25268v1 Announce Type: cross Abstract: Ranking is a fundamental component of modern information access systems.

By Yiteng Tu, Weihang Su, Zitao Su, Yiqun Liu, Min Zhang, Qingyao Ai

reinforcement-learning

arXiv AI

Jul 29

The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem

arXiv:2604. 14990v2 Announce Type: replace Abstract: The prospect of Artificial General Intelligence (AGI) is increasingly driving institutional decisions, and alignment of AGI is a hard problem.

By Till Mossakowski, Helena Esther Grass

agents reinforcement-learning safety

arXiv AI

Jul 29

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension

arXiv:2512. 06276v3 Announce Type: replace-cross Abstract: Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description.

By Tianyi Gao, Hao Li, Han Fang, Xin Wei, Xiaodong Dong, Hongbo Sun, Ye Yuan, Zhongjiang He, Jinglin Xu, Jingmin Xin, Hao Sun

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jul 29

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

arXiv:2607. 25308v1 Announce Type: cross Abstract: Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR) relies on sparse final rewards that reveal little about which decisions determine success.

By Yu Wang, Yi-Kai Zhang, Wentao Shi, Ziang Ye, Yuchun Miao, Yueqing Sun, Qi Gu, Xunliang Cai, Lan-Zhe Guo, Han-Jia Ye, Fuli Feng

llms agents reinforcement-learning efficiency

arXiv AI

Jul 29

Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL

arXiv:2607. 25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results.

By Jiabao Ji, Yujian Liu, Li An, Rohit Jain, Gungor Polatkan, Siyu Zhu, Shiyu Chang

llms agents reinforcement-learning efficiency

arXiv AI

Jul 29

Context Assembly as the Controlled Variable: A Control-Theoretic View of Harness Policies for Frozen LLM Agents

arXiv:2607. 25408v1 Announce Type: new Abstract: A growing body of 2026 work applies control theory to LLM agents: Lyapunov-certified stability for tool-mediated controllers (Prinos et al.

By Debjyoti Paul

llms agents reinforcement-learning

arXiv AI

Jul 29

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

arXiv:2607. 25091v1 Announce Type: new Abstract: The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated.

By Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray

llms agents reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 29

LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation

arXiv:2607. 24780v1 Announce Type: new Abstract: Evaluating frontier LLMs is challenging: static benchmarks suffer from contamination and saturation -- leaving users unable to distinguish top models and developers blind to specific failure modes -- while human preference is subjective.

By Xingyu Chen, Rui Wang, Zhaopeng Tu, Liefeng Bo

llms reinforcement-learning benchmarks

arXiv AI

Jul 29

HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising

arXiv:2607. 24779v1 Announce Type: new Abstract: Online advertising bidding systems typically deploy multiple offline-trained expert models (e.

By Ji Wu, Yunshan Peng, Wentao Bai, Yunke Bai, Wenzheng Shu, Jinan Pang, Yanxiang Zeng, Xialong Liu

llms agents reinforcement-learning benchmarks safety

arXiv AI

Jul 29

Reinforcement Learning for Code Optimization

arXiv:2607. 25970v1 Announce Type: cross Abstract: RL for code correctness is now established: have the model generate a program, run it against hidden test cases, and reward solutions that pass.

By Pierre Chambon, Kunhao Zheng, Juliette Decugis, Benoit Sagot, Gabriel Synnaeve

reinforcement-learning efficiency

arXiv AI

Jul 29

DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification

arXiv:2607. 25069v1 Announce Type: cross Abstract: Automated verification of numerical claims is a challenging problem, as it requires both language understanding and quantitative reasoning.

By Sagnik Sinha, Shreyas Shrestha

llms reinforcement-learning fine-tuning

arXiv AI

Jul 29

Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification

arXiv:2607. 25904v1 Announce Type: new Abstract: Graphical user interface task evaluation aims to determine whether a GUI agent has successfully completed a user instruction.

By Chenrui Shi, Yuwei Wu, Yang Liu, Ruining Feng, Zirui Shang, Zhi Gao, Lifeng Fan, Che Sun

agents reinforcement-learning benchmarks

arXiv AI

Jul 29

Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning

arXiv:2607. 24996v1 Announce Type: cross Abstract: Neural networks are hindered by accumulating dormant neurons and loss of expressivity throughout training, particularly in non-stationary data settings, such as continual supervised and reinforcement learning.

By Luc McCutcheon, Evangelos Chatzaroulas, Saber Fallah

reinforcement-learning benchmarks