Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Lin Yao

Lin Yao

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

NLP×3AI×2ML×1Vision×1

Frequent co-authors

Baolin Peng2×
Qianhui Wu2×
Hao Cheng2×
Wenlin Yao2×
Jianfeng Gao2×
Xiao Yu1×

Research Timeline

2026
Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading

The paper analyzes order-agnostic language models (OALMs), finding that their learned conditionals are not true factorizations and proposing a variance-based diagnostic to compare the quality of different decoding paths.

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performance on challenging web benchmarks.

OpenForgeRL: Train Harness-native Agents in Any Environment

OpenForgeRL is an open-source framework for training harness-based AI agents end-to-end in various environments using a lightweight proxy and Kubernetes orchestrator.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLEmpiricalRecentJul 23, 2026

OpenForgeRL: Train Harness-native Agents in Any Environment

Xiao Yu, Baolin Peng, Ruize Xu, Hao Zou +6 more

OpenForgeRL is an open-source framework for training harness-based AI agents end-to-end in various environments using a lightweight proxy and Kubernetes orchestrator.

View →
cs.LGcs.AIcs.CLRecent
Jun 1, 2026

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai +6 more

The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performan…

View →
cs.CLRecentMay 31, 2026

Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading

Lin Yao

The paper analyzes order-agnostic language models (OALMs), finding that their learned conditionals are not true factorizations and proposing a variance-based diagnostic to compare the quality of diffe…

View →