Consensus Is Strategically Insufficient: Reasoning-Trace Disagreement in Multi-Agent Systems

Paper Overview

Field: Machine Learning Authors: Michał Wawer, Jarosław A. Chudziak Published: 2025-06-01 arXiv: 2506.00633

Summary

Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. The authors argue that this objective is insufficient for value-laden tasks, where disagreement may reflect genuine normative uncertainty rather than agent error.

Building on prior work on reasoning-trace disagreement in human-AI collaborative moderation, the paper proposes a knowledge-representation layer in which reasoning traces and agent decisions are abstracted into symbolic disagreement states. Given agents producing explicit reasoning traces and binary decisions, four states are distinguished according to reasoning similarity and conclusion agreement:

• Convergent agreement — same conclusion, similar reasoning
• Divergent agreement — same conclusion, different reasoning
• Convergent disagreement — different conclusions, similar reasoning
• Divergent disagreement — different conclusions, different reasoning

These states support defeasible strategic routing rules. The framework is instantiated in content moderation, where disagreement-aware routing provides a bridge between sub-symbolic LLM reasoning and symbolic knowledge representation for strategic multi-agent reasoning.

Original Abstract (excerpt)

> Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue that this objective is insufficient for value-laden tasks, where disagreement may reflect genuine normative uncertainty rather than agent error...