Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Paper • 2610.08215 • Published • 98
Ryan Johnson
ryanjohns
·
AI & ML interests
None yet
Recent Activity
liked a model about 12 hours ago
autotrust/JEV-27B-VL upvoted a paper about 12 hours ago
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? upvoted a paper about 12 hours ago
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence MatchingOrganizations
None yet
upvoted 2
papers about 12 hours ago
upvoted 3
papers 7 days ago
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 413
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 378
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Paper • 2609.36585 • Published • 68