Harnessing Disagreement: Detecting Correlated Agreement Blindness in Multi-Agent Triage

arXiv:2607.19899 · cs.MA, cs.LG · Submitted 2026-07-22 · Read on arXiv

cs.MA, cs.LG

Submitted: 2026-07-22

Updated: 2026-07-22

Comments: 14 pages, 2 figures, 3 tables. Accepted at PAAMS 2026; this is the author's pre-review submitted version

Journal ref: Advances in Practical Applications of Agentic AI and Multi-Agent Systems, The PAAMS Collection: PAAMS 2026, Lecture Notes in Artificial Intelligence, vol. 17174, Springer, Cham, pp. 266-278, 2027

DOI: 10.1007/978-3-032-41794-7_21

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ablation — 1× in this paper · explained in 1 episode
• Arbitrated Reasoning Agents for Alarm Triage — 1× in this paper

Related papers

• Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
• Auditable and Deployable Multi-Agent Motion Planning via Posetal Games from Legal Guidelines
• ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
• You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
• Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
• MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization