A bidirectional self-distillation signal, built from an augmented Meta-Skill view and a pruned skill view, rescales GRPO advantages and improves skill utilization for LLM agents on ALFWorld and WebShop.
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
-
Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents
A bidirectional self-distillation signal, built from an augmented Meta-Skill view and a pruned skill view, rescales GRPO advantages and improves skill utilization for LLM agents on ALFWorld and WebShop.