Metraipolis › archive › dc_9edd4b13ef2a

ReCite: Agentic Reasoning for Faithful Citation — arXiv:2609.09156

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09156
License (as archived)
CC0-1.0
Archived
2026-10-16T12:49:35.582Z
SHA-256 of the archived text
72960c547e6df365402fb7bafe6d0616502471dddbe23acc16f6840469fda6a1
Stable URL of this page
https://metraipolis.com/documento/dc_9edd4b13ef2a

How to cite

ReCite: Agentic Reasoning for Faithful Citation — arXiv:2609.09156 — arXiv (en), https://arxiv.org/abs/2609.09156 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9edd4b13ef2a (Metraipolis archive dc_9edd4b13ef2a, sha256 72960c547e6df365402fb7bafe6d0616502471dddbe23acc16f6840469fda6a1)
BibTeX
@misc{dc9edd4b13ef2a,
  title = {ReCite: Agentic Reasoning for Faithful Citation — arXiv:2609.09156},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09156},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9edd4b13ef2a; sha256 72960c547e6df365402fb7bafe6d0616502471dddbe23acc16f6840469fda6a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09156. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate citations are the foundation of academic writing, tracing intellectual origins and substantiating core claims. However, manually navigating the growing volume of scientific literature is increasingly difficult, prompting reliance on automatic citation recommendation. While modern retrieval-augmented architectures have largely mitigated the fabrication of non-existent papers, current systems relying on semantic similarity struggle with misattribution, often citing authentic papers that fail to logically support the author's claim. To address this challenge, we argue that accurate citation requires a shift from similarity-based search to active, claim-level reasoning. We propose ReCite, a decoupled agentic framework that orchestrates location perception, intent-aware query planning, and reflective verification. Trained on synthesized reasoning trajectories, our agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments demonstrate that our lightweight framework outperforms state-of-the-art massive generative models in strict citation accuracy. By grounding literature matching in verifiable logic rather than semantic overlap, ReCite establishes a reliable foundation for automated academic writing.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.09156 — 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 2026-10-16T12:30:25.221Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).