mlsanityData to 7 Oct 2026

BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems

arXiv 2607.01600 ↗First posted 2 Jul 2026cs.LG cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

As large language models (LLMs) are deployed as communicating agents, does inter-agent communication cause outputs to converge? We introduce BOUNDARY_SYNC, a protocol measuring representational coupling via the Coupling Amplification Factor (CAF = JSD_cond / JSD_baseline), where CAF < 1 indicates homogenization and CAF > 1 indicates diversification. In controlled GPT-4o experiments (N=30, ~9,900 API calls), we measure coupling in text and image communication. Key findings: (1) text communication causes significant homogenization (CAF=0.803 [0.740, 0.873], d=1.30, p<0.001), confirmed by no-communication ablation and prompt-perturbation controls; (2) image communication also homogenizes under within-modality baselines (CAF=0.834 [0.811, 0.858]), with comparable proportional effect; (3) group size moderates coupling direction -- K=5 produces homogenization while K=3 yields CAF > 1.0 (point estimates 1.14 and 1.06, CI pending), suggesting a directional shift toward diversification; (4) cross-model replication shows extreme variation (CAF 0.034-0.803), with DeepSeek dominated by format artifacts; (5) coupling is stateless -- driven by prompt context rather than cumulative updating, with continuous consensus producing monotonic convergence. These results establish LLM agent coupling as real, measurable, and controllable at the prompt level, with direct implications for multi-agent system design.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 17 of its 29 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

17 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity3 Feb
  2. 2025Emergent Convergence in Multi-Agent LLM Annotation17 Nov
  3. 2024Exploring and Controlling Diversity in LLM-Agent Conversation30 Dec
  4. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 13

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 297
  5. 2025Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debatecited by 63
  6. 2025Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systemscited by 15
  7. 2025LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactionscited by 14
  8. 2025When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMscited by 14
  9. 2025The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systemscited by 11
  10. 2026The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Modelscited by 6
  11. 2025Towards Simulating Social Influence Dynamics with LLM-based Multi-agentscited by 3
  12. 2026Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensuscited by 3
1 more
  1. 2024Interacting Large Language Model Agents. Interpretable Models and Social Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The Contagion Tensor: A Framework for Measuring Output-Distribution Coupling in Multi-Agent LLM Systems -- and Auditing the Claims It Enables
  2. 2026Latent Communication Between Language Model Agents: Channels, Alignment, and the Limits of Text
  3. 2024COMMA: A Communicative Multimodal Multi-Agent Benchmark
  4. 2025Interaction Dynamics as a Reward Signal for LLMs
  5. 2024LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
  6. 2026CRAFT: Grounded Multi-Agent Coordination Under Partial Information
  7. 2026Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
  8. 2025Echoing: Identity Failures when LLM Agents Talk to Each Other