Preprint
The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment
ArXiv.org
07 Jun 2026
Abstract
Multi-agent LLM systems for medical question answering often treat consensus as a reliability signal: if multiple agents agree on an answer, it is presumed trustworthy. However, answer-level consensus does not entail reasoning-level alignment. We introduce CARA (Cross-Agent Reasoning Alignment), a family of automated metrics that measure whether agents who agree on an answer also agree on the reasoning. Applying CARA to a standard debate system on two medical QA benchmarks, MedQA-USMLE and MedThink-Bench, we identify the consistency illusion: a failure mode where debate reduces detectable contradictions between agents while simultaneously decreasing the semantic similarity of their reasoning chains; agents appear to agree more but reason less consistently. To improve this misalignment, we propose the Grounded Debate Protocol (GDP), a prompt-level intervention that requires agents to commit to named medical facts and take explicit stances on other agents' claims. GDP produces large, consistent alignment improvements, with Cohen's d ranging from +1.43 to +1.99, across two datasets and two backbone models, without adding LLM calls or modifying system architecture. Our results motivate cross-agent reasoning alignment as a quantity to audit alongside accuracy in safety-critical domains.
Metrics
1 Record Views
Details
- Title
- The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment
- Creators
- Xiaoyang Wang - Drexel UniversityChristopher C Yang - Drexel University
- Publication Details
- ArXiv.org
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Information Science; College of Computing and Informatics
- Other Identifier
- 991022191280004721