OGLS-SD improves LLM reasoning by using verifiable outcome rewards to guide logit steering that calibrates teacher distributions in on-policy self-distillation, addressing reflection-induced mismatches.
Reflexion: language agents with verbal reinforcement learning , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
OGLS-SD improves LLM reasoning by using verifiable outcome rewards to guide logit steering that calibrates teacher distributions in on-policy self-distillation, addressing reflection-induced mismatches.