Reinforcement learning

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

3,577 stories · RSS feed

arXiv AI

Jul 28

Offline-Online Curriculum RL for Multimodal Reasoning

arXiv:2607. 23700v1 Announce Type: new Abstract: Multimodal large language models exhibit capabilities on reasoning tasks, yet often produce flawed intermediate steps while yielding correct final answers.

By Wendi Deng, Hang Du, Guoshun Nan, Haokun Tian, Jiaqi Yu, Xinlei Cao, Jaile Li, Jingfeng Chen, Ling Deng, Ting Li, Hao Yang, Jun Liu, Xudong Jiang, Sicong Leng

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jul 28

Not All LLM Reasoning is Visible in the Chain-of-Thought

arXiv:2607. 22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens.

By Vatsal Baherwani, Tom Goldstein, Ashwinee Panda

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jul 28

Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning

arXiv:2602. 01348v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit.

By Yu Liu, Wenxiao Zhang, Diandian Guo, Cong Cao, Fangfang Yuan, Qiang Sun, Yanbing Liu, Jin B. Hong, Zhiyuan Ma

rag nlp reinforcement-learning benchmarks safety

arXiv AI

Jul 28

PathScale-R1: Cross-scale Reasoning for Pathological Image Analysis

arXiv:2607. 23794v1 Announce Type: cross Abstract: Pathological diagnosis is inherently multi-scale, requiring the integration of global tissue architecture at low magnification with cellular morphology at higher magnification.

By Chi Phan, Tianyi Zhang, Yufeng Wu, Qiaochu Xue, Jiajie Zhang, Linghan Cai, Zeyu Liu, Sudong Wang, Yueming Jin, Dan Hu

llms nlp reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jul 28

Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias

arXiv:2607. 22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data.

By Ofek I. Cohen, Lior Shani, Aviv Rosenberg, Ankur Samanta, Tal Wagner, Yonathan Efroni

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 28

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.

By James Elcock, William F. Shen, Xinchi Qiu, Nicholas D. Lane

llms reinforcement-learning fine-tuning safety

arXiv AI

Jul 28

ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning

arXiv:2607. 24062v1 Announce Type: cross Abstract: Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and inference.

By Wenwu Fan, Qihong Lin, Zhijie Xia, Zhuo Zheng, Sihao Wang, Qiang Chen, Liangsheng Zhu

llms reinforcement-learning efficiency

arXiv AI

Jul 28

Label-free Industrial Fault Detection via Adversarial Inverse Reinforcement Learning: A System for Run-to-Failure Prognostics

arXiv:2607. 22987v1 Announce Type: cross Abstract: Machinery fault detection (MFD) remains heavily reliant on supervised learning, which struggles with the scarcity of fault labels in real-world settings.

By Dhiraj Neupane, Mohamed Reda Bouadjenek, Richard Dazeley, Sunil Aryal

reinforcement-learning benchmarks safety

arXiv AI

Jul 28

DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification

arXiv:2607. 22644v1 Announce Type: new Abstract: Real-world document classification pipelines typically apply the same sequence of models to every incoming document, regardless of its complexity or type.

By Mohammed Yousif, Prabhjot Singh, Arjun Pankajakshan, Madhu Reddiboina

llms computer-vision reinforcement-learning benchmarks

arXiv AI

Jul 28

TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning

arXiv:2509. 06278v4 Announce Type: replace Abstract: Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations.

By Chuang Jiang, Mingyue Cheng, Xiaoyu Tao, Qingyang Mao, Jie Ouyang, Qi Liu

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 28

Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance

arXiv:2607. 22667v1 Announce Type: new Abstract: This paper presents an information-gain-guided reinforcement-learning sensor-selection framework for single-vessel tracking in heterogeneous maritime sensor networks.

By Andrei Starodubov, Yaqub Aris Prabowo, Andreas Hadjipieris, Roberto Galeazzi, Ioannis Kyriakides

agents reinforcement-learning

arXiv AI

Jul 28

In-Context Learning as Implicit Policy Gradient

arXiv:2607. 23153v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) can iteratively improve their outputs by incorporating generated samples and their corresponding evaluation scores as in-context examples.

By Masahiro Kaneko, Timothy Baldwin

llms reinforcement-learning

arXiv AI

Jul 28

MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents

arXiv:2607. 24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model.

By Yiwen Ma, Songjun Tu, Qichao Zhang, Dong Li, Linjing Li, Dongbin Zhao

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 28

Training Language Models to Cooperate with Inference-Time Controllers

arXiv:2607. 23771v1 Announce Type: new Abstract: Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning.

By Moumita Choudhury, Vanshaj Khattar, Jing Liu, Toshiaki Koike-Akino, Ankush Chakrabarty, Shlomo Zilberstein, Ye Wang

llms reinforcement-learning

arXiv AI

Jul 28

HiLLTS: Zero-Shot Hierarchical LLM-Guided Traffic Signal Control for Sustainable Transportation

arXiv:2607. 22691v1 Announce Type: new Abstract: Urban traffic congestion significantly increases fuel consumption, greenhouse gas emissions, and commuter delays, resulting in substantial economic losses and environmental harm in modern cities.

By Yue Ding, Tendai Mukande, Mingming Liu

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 28

When Every Simulation Counts: Value-Based Reinforcement Learning for Accelerated Photonics Inverse Design

arXiv:2607. 23469v1 Announce Type: cross Abstract: Photonic-crystal surface-emitting lasers (PCSELs) can combine high-power operation with narrow-divergence surface emission, but optimizing coupled parameters requires costly full-wave simulations.

By Longying Wen, Feiyang Wu, Jinglin Yu, Chongxian Yuan, Renjie Li, Zhaoyu Zhang

reinforcement-learning

arXiv AI

Jul 28

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning

arXiv:2607. 22996v1 Announce Type: cross Abstract: Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes.

By Xiaokun Wang, Siyu Song, Wentao Liu, Xiaodong Zou

llms reinforcement-learning safety

arXiv AI

Jul 28

Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction

arXiv:2607. 18985v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge.

By Jialian Li, Junhong Liu, Yuchen Cao, Weiran Guo, Jiaming Song, Xutao Wang, Yi Zhao, Jiangpin Liu, Jie Chen

llms agents reinforcement-learning robotics fine-tuning benchmarks

arXiv AI

Jul 28

Cortex: Compact Behavior Cloning for Quake with Frozen Visual Features

arXiv:2607. 22739v1 Announce Type: cross Abstract: We study how far a deliberately simple behavioral-cloning policy can progress in a visually rich first-person game before adding reinforcement learning or explicit memory.

By Dzmitry Malyshau

llms reinforcement-learning

arXiv AI

Jul 28

Traceable LLM Reasoning for Fake-Order Fraud Detection

arXiv:2607. 23075v1 Announce Type: cross Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability.

By Siqi You, Bingsong Xu, Zhixian Zheng, Xinjian Peng, Yang Xie, Ying Wang, Jiarong Xu

llms reinforcement-learning fine-tuning safety

Get the daily briefing