Metraipolis › archive › dc_6969448e70af
CARA: Causally Guided Retrieval Agent for Question Answering — arXiv:2610.22017
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22017
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:04:09.591Z
- SHA-256 of the archived text
c5176b7226d4a3ceb3de71926cf2c4af91171c2972a7870e4902bc1b7f7d4688- Stable URL of this page
https://metraipolis.com/documento/dc_6969448e70af
How to cite
CARA: Causally Guided Retrieval Agent for Question Answering — arXiv:2610.22017 — arXiv (en), https://arxiv.org/abs/2610.22017 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6969448e70af (Metraipolis archive dc_6969448e70af, sha256 c5176b7226d4a3ceb3de71926cf2c4af91171c2972a7870e4902bc1b7f7d4688)
BibTeX
@misc{dc6969448e70af,
title = {CARA: Causally Guided Retrieval Agent for Question Answering — arXiv:2610.22017},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22017},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6969448e70af; sha256 c5176b7226d4a3ceb3de71926cf2c4af91171c2972a7870e4902bc1b7f7d4688},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22017. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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, assessing whether removing evidence weakens answerability. CARA integrates these assessments with path consistency to guide graph exploration and employs reciprocal rank fusion to aggregate evidence from multiple agents. We evaluate CARA on three STaRK datasets and augment STaRK with ground-truth answers to enable downstream question answering evaluation. Experimental results demonstrate that CARA consistently outperforms existing retrievers. CARA also improves answer quality and faithfulness while examining fewer graph nodes and requiring fewer retrieval operations. These findings demonstrate that causal relevance assessment enables more focused and effective agentic graph retrieval, improving both retrieval performance and downstream question answering. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2610.22017 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:17.801Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).