Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
Paper • 2607.18722 • Published • 31
Ruhan Wang
ruhwang
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning authored a paper 3 days ago
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and EditableOrganizations
None yet
authored a
paper 1 day ago
upvoted a paper 2 days ago
authored 4
papers 3 days ago
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Paper • 2607.13285 • Published • 216
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Paper • 2607.08964 • Published • 74
Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models
Paper • 2503.16734 • Published • 1
LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models
Paper • 2309.14393 • Published
upvoted a paper 7 days ago
commented 2
papers 8 days ago