Metraipolis › archive › dc_c59c7f7fc2ea

BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation — arXiv:2609.35551

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35551
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:53.577Z
SHA-256 of the archived text
291feeceef77e254d77a3050107d99e283b019d0ecb1967abc2354bf4a1dfbe7
Stable URL of this page
https://metraipolis.com/documento/dc_c59c7f7fc2ea

How to cite

BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation — arXiv:2609.35551 — arXiv (en), https://arxiv.org/abs/2609.35551 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c59c7f7fc2ea (Metraipolis archive dc_c59c7f7fc2ea, sha256 291feeceef77e254d77a3050107d99e283b019d0ecb1967abc2354bf4a1dfbe7)
BibTeX
@misc{dcc59c7f7fc2ea,
  title = {BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation — arXiv:2609.35551},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35551},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c59c7f7fc2ea; sha256 291feeceef77e254d77a3050107d99e283b019d0ecb1967abc2354bf4a1dfbe7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35551. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In multi-agent systems, reliable consultation is challenging because advisor capabilities vary across tasks, and misleading information can make consultation worse than autonomous reasoning. We introduce BaRe-Mem, an online Bayesian reliability memory for multi-agent consultation. It estimates advisor reliability based on the central model's internal belief representations and updates these estimates from historical interactions. These estimates modulate the influence of advisor responses and guide the choice between consultation and autonomous reasoning. Across nine benchmarks and six central models, BaRe-Mem is more robust to misleading advisor information than debate and majority voting. On the more challenging tasks, it remains above autonomous reasoning across all tested misleading levels. Moreover, we extend the BaRe-Mem mechanism to worker allocation in agent teams. On the MuSiQue benchmark, BaRe-Mem improves task completion over routing by historical success counts and identifies capable workers earlier.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35551 — 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 2026-10-07T20:29:01.884Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).