Preprint
Aug 2026
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
TurnSight is proposed, a turn-level hindsight self-distillation framework that derives supervision directly from execution-conditioned hindsight and selects reliable supervision through cross-horizon directional agreement.
Changle Qu, Sun-Hao Dai, Hengyi Cai et al.
· 0 citations