Reinforcement learning

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

6,740 stories · RSS feed

arXiv Computer Vision

Sep 30

LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning

arXiv:2609.36219v1 Announce Type: new Abstract: Perspective taking is a fundamental component of spatial intelligence, requiring models interpret spatial relations from a specified viewpoint, such as...

By Bang Xiao, Wenqi Jia, Ozgur Kara, Tiancheng Shen, Yibo Yang, Bolin Lai, Junho Kim, James Matthew Rehg

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv Computer Vision

Sep 30

CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation

arXiv:2609.36616v1 Announce Type: new Abstract: Historical street-view imagery records urban evolution, but uneven coverage leaves substantial gaps in historical records. Generating plausible past ap...

By Hanwen Lu, Jun He, Mingjia Yang, Hao Wei, Jinhao Huang, Yi Lin, Xiang Zhang

reinforcement-learning fine-tuning safety

arXiv Computer Vision

Sep 30

Beyond Binary Preferences: Graded Preference Optimization for Limb-Motion Captioning

arXiv:2609.36628v1 Announce Type: new Abstract: Vision-Language Models (VLMs) can generate rich video captions, yet often misidentify which person performs an action or which limb is involved, partic...

By Yanan Wang, Tingsong Li, Kaixun Jiang, Chongyang Zhong, Chenwei Xoe, Zhaohe Liao

llms reinforcement-learning multimodal benchmarks safety

arXiv Computer Vision

Sep 30

DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning

arXiv:2609.36775v1 Announce Type: new Abstract: Reinforcement Learning has significantly advanced the complex reasoning capabilities of MLLMs. However, prevailing RL algorithms suffer a severe failur...

By Cheng Ye, Weidong Chen, Bingyan Xu, Zhendong Mao

reinforcement-learning benchmarks safety

arXiv Computer Vision

Sep 30

HaPRL: Human-Anchored Process Reinforcement Learning for Visual Search Agent

arXiv:2609.37190v1 Announce Type: new Abstract: Multi-turn visual search agents answer questions about high-resolution images by iteratively deciding where to look. Reinforcement learning for these a...

By Zhangquan Chen, Yaoxin Niu, Xiang An, Mingze Sun, Zhumei Wang, Chih-Ting Liao, Hongkun Cao, Ruqi Huang

agents reinforcement-learning

arXiv Computer Vision

Sep 30

MG-Thinker: Bi-Axial Self-Reflection for Multi-Image Reasoning Grounding

arXiv:2609.37374v1 Announce Type: new Abstract: Reinforcement learning (RL) has recently delivered substantial gains in multimodal reasoning, opening a promising route for fine-grained visual percept...

By Heyu Huang, Chi Chen, Zonghao Guo, Yuhua Li, Maosong Sun, Ruixuan Li

reinforcement-learning multimodal benchmarks

arXiv Computer Vision

Sep 30

HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents

arXiv:2609.38008v1 Announce Type: new Abstract: Computer use agents (CUAs) have demonstrated strong capabilities in completing digital tasks. However, existing CUAs either rely solely on graphical us...

By Tongbo Chen, Junbo Niu, Zhengxi Lu, Niu Lian, Fei Tang, Yuchen Yan, Yike Hong, Yong Du, Yizhou Liu, Bofan Chen, Yongliang Shen

agents reinforcement-learning fine-tuning

arXiv Computer Vision

Sep 30

Think, Then Look: Active Spatial Reasoning for House-Scale 3D Scene Understanding

arXiv:2512.03284v2 Announce Type: replace Abstract: Spatial reasoning in large-scale 3D environments remains challenging for current vision--language models, which are typically constrained to room-s...

By Hongpei Zheng, Shijie Li, Lin Qian, Zhenghao Li, Qijun Yang, Yanran Li, Hujun Yin

llms reinforcement-learning fine-tuning benchmarks

arXiv Computer Vision

Sep 30

SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation

arXiv:2609.33399v2 Announce Type: replace Abstract: In realistic education, a solution is often expressed not only in words but in a drawing--a circuit, a geometric construction, a function plot--and...

By Jiali Chen, Zhengteng Lin, Zuqi Wang, Shirong Lin, Xi Yu, Xusen Hei, DingBa Fu, Jiayuan Xie, Yi Cai

diffusion reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Sep 30

NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters

arXiv:2609.37038v1 Announce Type: cross Abstract: Precipitation nowcasting demands accurate short-term forecasts under strong spatiotemporal variability. Diffusion models are well suited to modeling...

By Haoran Xu, Xingzhuo Guo, Yuchen Zhang, Jincheng Zhong, Jianmin Wang, Mingsheng Long

llms diffusion reinforcement-learning benchmarks

arXiv AI

Sep 30

Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden?

arXiv:2609.35897v1 Announce Type: new Abstract: The pursuit of recursive self-improvement (RSI) toward general intelligence is divided between macro-level language model scaling and the interaction-d...

By Haomin Luo (University of Cambridge, Models2 AI)

llms reinforcement-learning benchmarks

arXiv AI

Sep 30

ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning

arXiv:2609.36238v1 Announce Type: new Abstract: A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Y...

By Nico Bohlinger, Jan Peters

rag agents reinforcement-learning robotics benchmarks

arXiv AI

Sep 30

RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation

arXiv:2609.36652v1 Announce Type: new Abstract: Open-ended generation lacks canonical answers, making pointwise rewards difficult to calibrate for group-based reinforcement learning. Directly ranking...

By Zixuan Yang, Yiqun Chen, Qi Liu, Wei Yang, Erhan Zhang, Liyi Chen, Qimeng Wang, Yan Gao, Jiaxin Mao

reinforcement-learning efficiency benchmarks

arXiv AI

Sep 30

EASE: Behavior-Adaptive Skill Curation for Self-Evolving Agents

arXiv:2609.36746v1 Announce Type: new Abstract: Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. Ho...

By Zhen Xiong, Qiaoyu Tan

llms agents reinforcement-learning fine-tuning

arXiv AI

Sep 30

Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post-Training

arXiv:2609.36830v1 Announce Type: new Abstract: Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation wi...

By Chenliang Li, Neiwen Ling, Zijun Wei, Alfredo Garcia

llms reinforcement-learning benchmarks

arXiv AI

Sep 30

SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents

arXiv:2609.36939v1 Announce Type: new Abstract: GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces. Existing group-relative reinforcement learning im...

By Shengtian Yang, Ziyu Xiong, Kaibing Yang, Guangfeng Cai, Yewen Li, Peng Jiang, Gai Kun, Qingpeng Cai, Lei Feng

agents reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Sep 30

Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents

arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested....

By Ido Levy, Asaf Yehudai, Segev Shlomov, Asaf Adi, Leshem Choshen

agents reinforcement-learning benchmarks

arXiv AI

Sep 30

Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback

arXiv:2609.37356v1 Announce Type: new Abstract: Generating optimization instances that are both feasible and computationally challenging is crucial for benchmarking solvers and training learning-base...

By Jitin Singla, Parikshit Pareek, Pratik Jawanpuria, Parag Singla

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Sep 30

MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators

arXiv:2609.37670v1 Announce Type: new Abstract: MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tu...

By Haocheng Tang, Tianchi Xie, Xingqiao Lin

reinforcement-learning fine-tuning efficiency

arXiv AI

Sep 30

Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL

arXiv:2609.37898v1 Announce Type: new Abstract: Reinforcement learning for long-horizon agents typically relies on sparse outcome-based rewards. This leads to a severe cold-start problem, as early-st...

By Youling Huang, Tiankuo Xu, Jiaji Liu, Tong Zheng, Shuo Zhou, Shaotong Qi, Junchi Yao, Shiyang Liu, Hao Xu, Pengcheng Xu, Bo Huang, Hongyi Fu, Lin Lin

agents reinforcement-learning efficiency

Get the daily briefing