What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems

Yong Jin Chun, Iftekhar Ahmed
5/19/2026
cs.MA

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error propagation, where early-stage information degrades downstream reasoning. To address this, we conduct a systematic analysis of inter-agent communication to identify which information drives MA performance. We find that the absence of reasoning and verification in inter-agent communication significantly degrades performance. Based on these insights, we propose Category-Aware Recovery Augmentation (technique), which enforces the presence of critical information during communication. recovers up to 86.2% of failed cases. Our results highlight the key role of information quality in effective MA collaboration. Our code is available at https://anonymous.4open.science/r/cara_mas

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Misinformation Propagation in Benign Multi-Agent Systems

85% match1 repo22026

Robust Multi-Agent LLMs under Byzantine Faults

84% match2026

CRAFT: Grounded Multi-Agent Coordination Under Partial Information

83% match1 repo72026

ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures

83% match2026

More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration

83% match2026

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

83% match2026

Cite this paper

@article{chun2026what,
  title  = {What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems},
  author = {Yong Jin Chun and Iftekhar Ahmed},
  year   = {2026},
  eprint = {2605.20548},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2605.20548v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2605.20548.svg)](https://codeofpaper.com/paper/2605.20548)

Discussion