HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 8 天前AI 评分40
BaRe-Mem：面向多智能体咨询的贝叶斯可靠性记忆
AI 导读
BaRe-Mem 是一种面向多智能体咨询的在线贝叶斯可靠性记忆，基于中心模型的内部信念表示估计顾问可靠性，并用历史交互更新这些估计，从而调节顾问回答的影响、决定是咨询还是自主推理。
正文
Abstract: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.
| Comments: | BaRe-Mem is an online Bayesian reliability memory that learns context-dependent advisor reliability from verified interactions, modulates external advice accordingly, and adaptively decides whether to consult or reason autonomously |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.35551 [cs.AI] |
| (or arXiv:2609.35551v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.35551 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Peilin Feng [view email]
[v1]
Mon, 28 Sep 2026 16:25:16 UTC (968 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org