#ModelSuccess ratePaper
1What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents80.10β€”
2Hindsight Credit Assignment for Long-Horizon LLM Agents7.70β€”
3SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment4.40β€”
WebShop webshop Leaderboard