TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-level supervision, limiting fine-grained credit assignment in long-horizon TIR scenarios. On-policy self-distillation offers denser signals through teacher branches with privileged context, but existing approaches…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
