Metraipolis › archive › dc_f29c0bbfacc1

SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving — arXiv:2611.08196

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08196
License (as archived)
CC0-1.0
Archived
2026-11-06T14:41:54.783Z
SHA-256 of the archived text
96ec87520b4f4449cb2254c59d8d3f4ecc24b4bfda53bf8c528d78a39f9f9083
Stable URL of this page
https://metraipolis.com/documento/dc_f29c0bbfacc1

How to cite

SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving — arXiv:2611.08196 — arXiv (en), https://arxiv.org/abs/2611.08196 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f29c0bbfacc1 (Metraipolis archive dc_f29c0bbfacc1, sha256 96ec87520b4f4449cb2254c59d8d3f4ecc24b4bfda53bf8c528d78a39f9f9083)
BibTeX
@misc{dcf29c0bbfacc1,
  title = {SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving — arXiv:2611.08196},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08196},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f29c0bbfacc1; sha256 96ec87520b4f4449cb2254c59d8d3f4ecc24b4bfda53bf8c528d78a39f9f9083},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08196. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Complex problems with limited context, such as claims, require a means to obtain additional knowledge necessary for solution reasoning. We propose a multi-agent framework, SMART, to obtain knowledge through capturing the implicit state of participating entities in a problem context. SMART curates the state knowledge as diverse, complementary and solution-salient premises using a variety of LLMs and a structured role-based prompt strategy. Using knowledge from these real-world verified curated premises, SMART's knowledge guided solution reasoning improves validation performance up to 20% on complex scientific claims spanning 3 datasets. We show that grounding premises in real-world knowledge is necessary and improves performance up to 5%.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.08196 — 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 2026-11-06T14:18:42.653Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).