More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
Paper • 2610.19789 • Published • 61
Tyler E. Garcia
tylergfg
·
AI & ML interests
Interested in machine learning, NLP and open source AI.
Recent Activity
updated a model 10 days ago
tylergfg/simple-retrieval published a model 10 days ago
tylergfg/simple-retrievalOrganizations
None yet
upvoted a paper 10 days ago
upvoted 3
papers 20 days ago
Does Learning Protein Folding Generalize to Broader Reasoning?
Paper • 2609.38879 • Published • 53
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 235
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 208