Contrastive Reflection identifies error-anchored slices in agent traces, adds contrastive successes, and uses a Teacher LLM to generate prompt edits that are accepted only if they improve validation performance, raising HotpotQA exact-match from 51.4% to 60.4%.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Contrastive Reflection for Iterative Prompt Optimization
Contrastive Reflection identifies error-anchored slices in agent traces, adds contrastive successes, and uses a Teacher LLM to generate prompt edits that are accepted only if they improve validation performance, raising HotpotQA exact-match from 51.4% to 60.4%.