Reinforcement learning

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

3,470 stories · RSS feed

arXiv AI

Aug 7

Learning When to Trust via Selective Context Preference Optimization

arXiv:2608. 06377v1 Announce Type: cross Abstract: Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong.

By Xian Sun, Wei Chow, Yingshuo Wang, Junhao Liu, Wei Gao, Qing Wu, Lingdong Kong

llms reinforcement-learning benchmarks

arXiv AI

Aug 7

iARCS: Iterative Agentic RL for Controllable 3D Scene Generation

arXiv:2608. 06161v1 Announce Type: new Abstract: Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably satisfying task-critical functional constraints.

By Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel

llms agents computer-vision reinforcement-learning robotics fine-tuning

arXiv AI

Aug 7

Cautious Context Steering for Language Model Personalization

arXiv:2608. 05813v1 Announce Type: new Abstract: Personalizing language models (LMs) to individual user preferences is essential for aligning responses with diverse goals and backgrounds.

By Gihoon Kim, Jeyoung Lee, Suhan Woo, Sekwon Oh, Minsu Jeon, Hyounsoo Han, Euntai Kim

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Aug 7

ProDVI: Programmatic Dynamics Priors for Value Network Initialization

arXiv:2608. 06015v1 Announce Type: cross Abstract: Deep Reinforcement Learning (RL) is notoriously sample inefficient.

By Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen

llms agents reinforcement-learning

arXiv AI

Aug 7

When Agentic AI Meets Integrated Sensing and Communication

arXiv:2608. 05792v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) is transforming Integrated Sensing and Communication (ISAC) from a function-oriented physical-layer technology into a goal-driven, closed-loop intelligent system, a paradigm we term AISAC.

By Kai Li, Conggai Li, Sarah Ali Siddiqui, Syed Sohail Ahmed, Xin Yuan, Shenghong Li, Wei Ni

llms agents reinforcement-learning multimodal benchmarks safety

arXiv AI

Aug 7

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

arXiv:2607. 28609v2 Announce Type: replace Abstract: Computer-using agents (CUAs) are advancing rapidly across the digital world.

By Qiushi Sun, Kanzhi Cheng, Yian Wang, Bowen Yang, Hang Yan, Liheng Chen, Fangzhi Xu, Zichen Ding, Nuo Chen, Jialin Cao, Xingdong Gong, Zehao Li, Kaiming Jin, Xinfeng Yuan, Zhoumianze Liu, Jingyang Gong, Zhangyue Yin, Jiahui Gao, Zhiyong Wu, Tianbao Xie, Jianbing Zhang, Ben Kao, Lingpeng Kong

llms agents reinforcement-learning multimodal benchmarks safety

arXiv AI

Aug 7

AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents

arXiv:2608. 05891v1 Announce Type: new Abstract: Mobile GUI agents can operate apps through pixel perception and touch actions, making them a promising interface for collecting and improving long-horizon mobile interaction policies.

By Weikai Xu, Yunren Feng, Haoxiang Lei, Kun Huang, Yuxuan Liu, Kang Zhao, Xiaolin Hu, Shuo Shang, Bo An

agents reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Aug 7

Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment

arXiv:2603. 16141v2 Announce Type: replace-cross Abstract: Autonomous Unmanned Aerial Vehicle (UAV) swarms are increasingly used as rapidly deployable aerial relays and sensing platforms, yet practical deployments must operate under partial observability and intermittent peer-to-peer connectivity.

By Enguang Fan, Yifan Chen, Zihan Shan, Klara Nahrstedt, Matthew Caesar, Jae Kim

agents reinforcement-learning

arXiv AI

Aug 7

Path Planning of Cleaning Robot with Reinforcement Learning

arXiv:2208. 08211v2 Announce Type: replace-cross Abstract: Recently, as the demand for cleaning robots has steadily increased, therefore household electricity consumption is also increasing.

By Woohyeon Moon, Bumgeun Park, Sarvar Hussain Nengroo, Taeyoung Kim, Dongsoo Har

reinforcement-learning robotics fine-tuning benchmarks

arXiv AI

Aug 7

Agentic Software Issue Resolution with Large Language Models: A Survey

arXiv:2512. 22256v2 Announce Type: replace-cross Abstract: Software issue resolution aims to address real-world issues in software repositories based on natural language descriptions provided by users, and represents a key aspect of software maintenance.

By Zhonghao Jiang, David Lo, Zhongxin Liu

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 7

Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic Shipping

arXiv:2608. 06105v1 Announce Type: cross Abstract: Artificial Intelligence (AI)-assisted navigation can help Arctic shipping adapt to rapidly changing sea-ice conditions, but reliable deployment requires reward models that are interpretable and robust to changing environments.

By Vaishnav Vaidheeswaran, Dilith Jayakody, Biruk Ambaw, Jaswanth Kumar, Md Mahbub Alam, Gabriel Spadon

reinforcement-learning benchmarks safety

arXiv AI

Aug 7

CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents

arXiv:2608. 05886v1 Announce Type: cross Abstract: Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it.

By Wuya Chen, Yihao yang, Yang Cao, Yue Lin

llms agents reinforcement-learning

arXiv AI

Aug 7

Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations

arXiv:2608. 05588v1 Announce Type: cross Abstract: Lifelong Multi-Agent Path Finding (LMAPF) requires repeatedly planning collision-free paths for agents that continuously receive new goals upon reaching their current ones.

By He Jiang, Jingtian Yan, Yulun Zhang, Yimin Tang, Tanishq Duhan, Rishi Veerapaneni, Guillaume Sartoretti, Jiaoyang Li

agents reinforcement-learning robotics safety

arXiv Machine Learning

Aug 7

Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently

arXiv:2511. 17852v3 Announce Type: replace Abstract: Transformers can acquire Chain-of-Thought (CoT) capabilities to solve reasoning tasks via fine-tuning.

By Bochen Lyu, Yiyang Jia, Xiaohao Cai, Zhanxing Zhu

llms reinforcement-learning fine-tuning

arXiv AI

Aug 7

Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks

arXiv:2608. 05340v1 Announce Type: cross Abstract: Time-Sensitive Networking (TSN) and Mobile Edge Computing (MEC) hold strong potential for enabling ultra-reliable low-latency communication for time-sensitive applications, such as eXtended Reality (XR).

By Marcos Carvalho, Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci, Daniel F. Macedo

llms agents reinforcement-learning

arXiv AI

Aug 7

Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution

arXiv:2608. 05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly.

By Sichun Luo, Yi Huang, Guanzhi Deng, Haibo Wang, Haochen Luo, Lei Li, Zefa Hu, Junlan Feng, Qi Liu

llms reinforcement-learning benchmarks

arXiv AI

Aug 7

Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application

arXiv:2608. 05346v1 Announce Type: cross Abstract: Time-sensitive networking (TSN) is increasingly integrated into mobile edge computing (MEC) to support applications with stringent latency requirements, such as extended reality (XR).

By Marcos Carvalho, Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci, Daniel F. Macedo

agents reinforcement-learning

arXiv AI

Aug 7

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models

arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.

By Kyuyoung Kim, Kevin Wang, Yunfei Xie, Peiyang Xu, Peiyao Sheng, Chen Wei, Zhangyang Wang, Jinwoo Shin, Pramod Viswanath, Sewoong Oh

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Aug 7

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

arXiv:2608. 05446v1 Announce Type: new Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.

By Xuying Ning, Dongqi Fu, Tianxin Wei, Hanqing Zeng, Yuanchen Bei, Bingxuan Li, Zihao Li, Qifan Wang, Xiang Shen, Yifan Wu, Jiayi Liu, Hong Li, Yinglong Xia, Xiangjun Fan, Hanghang Tong, Jingrui He

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Aug 7

SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models

arXiv:2608. 06179v1 Announce Type: new Abstract: Preference optimisation has proven effective for improving large language models but typically relies on costly human preference annotations.

By Hoda Fakharzadehjahromy, Emil Wiman, Andreas Bueff, Hafsteinn Einarsson, Fredrik Heintz

llms reinforcement-learning safety