HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

by [unverified] · free · Last verified 2026-06-21T03:07:54.392Z

Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermediate actions caused the outcome or how they should be corrected. Recent methods alleviate this issue by generating rewards or textual hi...