mlsanityData to 14 Oct 2026

MOC: Multi-Order Communication in LLM-based Multi-Agent Systems

arXiv 2606.02359 ↗First posted 1 Jun 2026cs.AIcited by 4

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

Abstract (arXiv)

Despite the remarkable progress of Large Language Model (LLM) based Multi-Agent Systems, most research focuses on optimizing coordination topology while largely underexploring the equally critical problem: how to transmit and optimize messages among agents effectively? Current communication schemes typically rely on the direct concatenation of first-order neighbor responses, which induces a restricted evidence receptive field and leads to the dilution of crucial insights over multi-hop paths. To address these limitations, we propose the Multi-Order Communication (MOC) scheme, which reconstructs the inter-agent communication to capture multi-hop dependencies and incorporates a structural message consolidation strategy to ensure efficiency. Specifically, we formalize the communication mechanism to construct a structured multi-order evidence stream, and subsequently design a Semantic-Topological Merging algorithm to optimize semantic fidelity within token constraints. Extensive experiments across six diverse datasets and LLM backbones of varying parameter scales demonstrate that MOC consistently improves task performance and reduces communication costs. The code is available at https://github.com/yao-guan/MOC.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 42 of its 48 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

42 of 48 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools7 Feb
  2. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  3. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application23 Dec
  4. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  5. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  7. 2023Agent Instructs Large Language Models to be General Zero-Shot Reasoners5 Oct
  8. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  11. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 31

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2017Graph Attention Networkscited by 8,923
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2017Inductive Representation Learning on Large Graphscited by 6,320
  9. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  10. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  11. 2023A Survey of Large Language Modelscited by 2,576
  12. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
19 more
  1. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  3. 2019Simplifying Graph Convolutional Networkscited by 1,477
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  5. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  6. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  7. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  8. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  9. 2023A Comprehensive Overview of Large Language Modelscited by 648
  10. 2024TinyLlama: An Open-Source Small Language Modelcited by 618
  11. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 523
  12. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  13. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  14. 2023How Language Model Hallucinations Can Snowballcited by 311
  15. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  16. 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systemscited by 59
  17. 2024Learning Multi-Agent Communication from Graph Modeling Perspectivecited by 48
  18. 2024Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?cited by 41
  19. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Social Circuits behind Multi-agent Echo Chamberscited by 0
  2. 2026Self-Adapting Group of Experts for Multi-Agent Reasoningcited by 0
  3. 2026CollabFlow: Recursive Self-Improvement of Agent Collaborationcited by 0
  4. 2026BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
  2. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
  3. 2026Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
  4. 2026Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
  5. 2026Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
  6. 2026Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication Topologies
  7. 2026SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models
  8. 2025Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems