cs.AINov 10, 2026

SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning

Authors: Zhiming Xue, Jianan Liu, Weiran Yan, Aicheng Xie, Jing Yang

Organizations: College of Engineering Northeastern University Boston, USA · Independent Researcher Austin, USA · Independent Researcher Santa Clara, USA · Independent Researcher San Jose, USA · 

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.

Figures & tables

Explore similar work

CardsList
  1. COVER: Identifiable Evaluation of Coalition Routing

    Aug 28, 2026Raghul Sugumar, Amrit GopinathAI Agent EvaluationLLM Agent Routing

  2. RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough

    Aug 5, 2026Anchen Sun, Kaiqi YangMulti-Agent LLM SystemsAI Agent Benchmarks