SOURCE-LINKED INTELLIGENCE
CARA: Causally Guided Retrieval Agent for Question Answering
Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merely matching its textual content. Existing agentic retrievers adaptively balance global search and multi-hop exploration but primarily rely on textual similarity to guide retrieval. We propose CARA, a training-free, CAusally guided Retrieval Agent that explicitly evaluates the causal relevance of retrieved evidence through two complementary criteria: consequentiality, measuring whether adding evidence improves answerability, and essentiality, ass
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-15T14:57:14.000Z
First collected: 2026-10-17T14:52:22.282Z. This is not the publication date.