SafeRoute-MAS：多智能体科学推理中基于覆盖与风险的消息路由方法
SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning
一篇关于多智能体消息路由的论文，SafeRoute-MAS 只用集成前信息删消息，能省 12.76% token 还提升 1.80 点成绩。但作者自己用 gpt-oss-120b 做的独立复现基本打平，还给出了诚实的资格判定机制。做多智能体系统、关心评估严谨性的人值得看看这套方法论。
论文提出 SafeRoute-MAS，一种覆盖感知、风险校准的消息路由机制，仅凭集成前信息决定保留或删除多智能体系统中的专家消息。在 5,328 个委员会的密封缓存上，其源兼容运行点带来 +1.80 个百分点增益（95% CI [+1.13, +2.52]），同时删除 12.76% 的消息 token。
作者还在公开的 gpt-oss-120b 端点上对 458 个委员会的分层样本跑了 4,580 次受控集成：原始样本估计为 -0.09 点，按原工作负载加权后为 +0.94 点（95% CI [-1.31, +3.50]），输入 token 减少 18.72%。token 配平的加权对比未证实选择器优势（+1.68 点，CI [-1.27, +5.10]）。88 个缓存非中性标签中仅 13 个（14.8%）在重复调用多数投票下保持方向。
加权后预期腐蚀 UCL 为 4.60%，但 11 个预设边际中只有 2 个通过支持/风险规则。作者据此提出带 Keep-All 回退的数值资格判定机制，并说明该机制在此为回溯性应用，尚未经过前瞻性验证。
SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning
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.
本条情报归属 AITOP「论文」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「各国 AI 监管法案、合规治理与主权算力政策」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：SafeRoute-MAS、gpt-oss-120b、多智能体、智能体，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Zhiming Xue, Jianan Liu, Weiran Yan, Aicheng Xie, Jing Yang），经 AITOP 多维评分管线结构化提炼。