Training LLM agents with reference-grounded self-distillation only at states matched to a successful trajectory improves task success on ALFWorld and WebShop over unconditionally applying the full reference.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
Training LLM agents with reference-grounded self-distillation only at states matched to a successful trajectory improves task success on ALFWorld and WebShop over unconditionally applying the full reference.