TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
By Changle Qu · Paper · cs.CL
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 s