Metraipolis › archive › dc_ea85e1da6b59
DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation — arXiv:2608.17282
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.17282
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:28:34.334Z
- SHA-256 of the archived text
6317a1a79abe2643adcd7bbd68b2d95cbb9440287ae866ef4831a2472a6e847b- Stable URL of this page
https://metraipolis.com/documento/dc_ea85e1da6b59
How to cite
DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation — arXiv:2608.17282 — arXiv (en), https://arxiv.org/abs/2608.17282 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea85e1da6b59 (Metraipolis archive dc_ea85e1da6b59, sha256 6317a1a79abe2643adcd7bbd68b2d95cbb9440287ae866ef4831a2472a6e847b)
BibTeX
@misc{dcea85e1da6b59,
title = {DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation — arXiv:2608.17282},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.17282},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea85e1da6b59; sha256 6317a1a79abe2643adcd7bbd68b2d95cbb9440287ae866ef4831a2472a6e847b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17282. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing agentic reasoning systems typically rely on centralized protocols. This design introduces routing bottlenecks and static role allocations that often fail when handling complex multimodal queries. We propose DeAR (Decentralized Agentic Reasoning), a framework that shifts from central control to autonomous peer-to-peer collaboration. DeAR is built on three mechanisms: (1) decentralized capability grounding for query-dependent agent specialization, (2) thought map navigation for targeted peer interactions, and (3) topology update for adaptive error correction. Evaluations across 9 diverse multimodal reasoning and text-based QA benchmarks indicate that DeAR consistently outperforms recent baseline methods, validating that decentralized and adaptive collaboration among agents enhances accuracy in knowledge-intensive reasoning tasks. The source code will be available at https://open_upon_acceptance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.17282 — 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 2026-10-18T14:27:54.249Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).