AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Beyond Correctness: Distance-Based Social Dynamics of Multi-Agent Debate

Seungwoong Ha, Melanie Mitchell

ICML 2026 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies microscopic answer-revision dynamics in multi-agent debate on ConceptARC grid-reasoning tasks, using quantitative distance between candidate solutions rather than binary correctness.

Problem

Multi-agent debate systems are typically evaluated with binary correctness or peer agreement, which obscures how individual agents revise answers during social interaction.

Approach

Uses ConceptARC, a 2D grid-reasoning benchmark whose candidate solutions admit quantitative distance measures, to analyze how LLM agents move toward or away from peer answers during debate.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
more wrong peers (scenario A, W3) shown to a correct target (ablation)correct target in multi-agent debate · ConceptARCretention of correct answerHurt
wrong peers repeat the same wrong answer instead of being diverse (ablation)correct target · ConceptARCretention of correct answerHurt
re-prompt without peers (self-reflection) for correct targets (ablation)DeepSeek-chat and GPT-5 mini · ConceptARCretention of correct answer: more than 70% retainedNo clear effect
all wrong peers identical to the target's wrong answer (sameWrong) (ablation)wrong target · ConceptARCanswer stabilityImproved
wrong peers differ from the target's wrong answer (ablation)wrong target · ConceptARCanswer retention: less than 10% retentionHurt
larger initial pixel distance to ground truthwrong target · ConceptARCprobability of changing answerImproved
larger initial distance, correction ratewrong target, DeepSeek-chat vs GPT-5 mini · ConceptARCprobability of correct revisionMixed
social revision of wrong answers (contraction)wrong target · ConceptARCchange in pixel distance after revisionImproved
wrong peers closer to the ground truthcorrect target, scenario A · ConceptARCprobability of changing answerHurt

Experimental setup

Datasets: ConceptARC

Benchmarks: ConceptARC

Metrics: distance between candidate solutions answer revision dynamics

Builds on: multi-agent debate

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy