PROGRESS adds a teacher-guided coverage reward to RL training, encouraging search-augmented LLMs to issue comprehensive, granular sub-queries and improving multi-hop QA accuracy by 2-5% absolute.
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
-
PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent
PROGRESS adds a teacher-guided coverage reward to RL training, encouraging search-augmented LLMs to issue comprehensive, granular sub-queries and improving multi-hop QA accuracy by 2-5% absolute.