SD-Search derives step-level supervision for search queries in reasoning agents via on-policy hindsight self-distillation using the policy as both student and teacher.
Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
SD-Search derives step-level supervision for search queries in reasoning agents via on-policy hindsight self-distillation using the policy as both student and teacher.