SafeRoute-MAS：面向多智能体科学推理的覆盖感知与风险校准消息路由方法
SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning
AI 导读
arXiv 论文提出 SafeRoute-MAS，一种覆盖感知、风险校准的多智能体消息路由方法，可在仅用集成前信息的情况下保留或剔除专家消息。
正文 · 原文
Abstract:We introduce SafeRoute-MAS, a coverage-aware, risk-calibrated procedure that keeps all specialist messages or removes one using only pre-integration information. On a sealed cache of 5,328 committees, its source-compatible operating point gains +1.80 percentage points (95% CI [+1.13, +2.52]) while removing 12.76% of message tokens. We also run 4,580 controlled integrations over a stratified 458-committee sample on a public gpt-oss-120b endpoint. The sample estimate is -0.09 points; design weighting to the original workload gives +0.94 points (95% CI [-1.31, +3.50]) and 18.72% acted-input reduction. A weighted token-matched comparison likewise does not establish a selector advantage (+1.68 points, CI [-1.27, +5.10]). Only 13 of 88 cached non-neutral labels (14.8%) retain direction by repeated-call majority. Expected-corruption UCL is 4.60% after weighting, but only 2 of 11 prespecified marginals pass the support/risk rule. We therefore propose a numerical qualification with Keep-All fallback, applied here retrospectively rather than validated prospectively.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13454 [cs.AI] |
| (or arXiv:2611.13454v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13454 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhiming Xue [view email]
[v1]
Tue, 10 Nov 2026 01:56:19 UTC (165 KB)
来源：arXiv cs.AI · arxiv.org