# When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation

arXiv: https://arxiv.org/abs/2604.03796 · HTML: https://mlsanity.com/paper/2604.03796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 4 of 4)

- [Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning](https://mlsanity.com/paper/2009.10277/) (2020)
- [Byzantine-Robust Decentralized Coordination of LLM Agents](https://mlsanity.com/paper/2507.14928/) (2025)
- [Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System](https://mlsanity.com/paper/2507.02170/) (2025)
- [Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness](https://mlsanity.com/paper/2603.06612/) (2026)

## Abstract (arXiv)

When LLM-based multi-agent systems disagree, current practice treats this as noise to be resolved through consensus. We propose it can be signal. We focus on hate speech moderation, a domain where judgments depend on cultural context and individual value weightings, producing high legitimate disagreement among human annotators. We hypothesize that convergent disagreement, where agents reason similarly but conclude differently, indicates genuine value pluralism that humans also struggle to resolve. Using the Measuring Hate Speech corpus, we embed reasoning traces from five perspective-differentiated agents and classify disagreement patterns using a four-category taxonomy based on reasoning similarity and conclusion agreement. We find that raw reasoning divergence weakly predicts human annotator conflict, but the structure of agent discord carries additional signal: cases where agents agree on a verdict show markedly lower human disagreement than cases where they do not, with large effect sizes (d>0.8) surviving correction for multiple comparisons. Our taxonomy-based ordering correlates with human disagreement patterns. These preliminary findings motivate a shift from consensus-seeking to uncertainty-surfacing multi-agent design, where disagreement structure - not magnitude - guides when human judgment is needed.