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
2 Pith papers cite this work, alongside 14 external citations. Polarity classification is still indexing.
2
Pith papers citing it
14
external citations · external index
years
2026 2verdicts
UNVERDICTED 2representative citing papers
K-CARE uses behavior-derived anchoring and expert prototype analogies to ground LLMs and improve relevance on knowledge-intensive e-commerce cases.
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%.
-
K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance
K-CARE uses behavior-derived anchoring and expert prototype analogies to ground LLMs and improve relevance on knowledge-intensive e-commerce cases.