mlsanityData to 7 Oct 2026

TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System

arXiv 2602.03688 ↗First posted 3 Feb 2026cs.AIcited by 5

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

Abstract (arXiv)

Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing methods employ a fixed communication topology during inference, which falls short in many realistic applications where the agents' roles may change textitacross rounds due to dynamic adversary, task progression, or time-varying constraints such as communication bandwidth. In this paper, we propose addressing this issue through TodyComm, a task-oriented dynamic communication algorithm. It produces behavior-driven collaboration topologies that adapt to the dynamics at each round, optimizing the utility for the task through policy gradient. Experiments on five benchmarks demonstrate that, under both dynamic adversarial settings and communication budget constraints, TodyComm achieves superior task performance while maintaining token efficiency, scalability, and strong generalizability across varying adversarial conditions.

Key facts. Cited by 5 papers in the map (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 34 of its 49 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

34 of 49 references.

Closest ancestors · 12

Same direction, newest first

  1. 2026ResMAS: Resilience Optimization in LLM-based Multi-agent Systems8 Jan
  2. 2025Latent Collaboration in Multi-Agent Systems25 Nov
  3. 2025SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication15 Aug
  4. 2025Adaptive Graph Pruning for Multi-Agent Communication3 Jun
  5. 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning7 Feb
  6. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks15 Oct
  7. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  8. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  9. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct
  10. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  11. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  12. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 22

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  5. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  6. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  8. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  9. 2016Variational Graph Auto-Encoderscited by 1,373
  10. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  11. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  12. 2018TarMAC: Targeted Multi-Agent Communicationcited by 201
10 more
  1. 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 114
  2. 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 89
  3. 2021ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mindcited by 57
  4. 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systemscited by 56
  5. 2023ChatLLM Network: More brains, More intelligencecited by 37
  6. 2025BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attackscited by 37
  7. 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Modelscited by 31
  8. 2020Learning Structured Communication for Multi-agent Reinforcement Learningcited by 21
  9. 2025PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solvingcited by 15
  10. 2025EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memorycited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 5
  2. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  3. 2026MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfercited by 0
  4. 2026Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoningcited by 0
  5. 2026Reinforcement Learning of Communication in a Mesh of Small Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
  2. 2026GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
  3. 2025AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
  4. 2026COOP2: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
  5. 2025Red-Teaming LLM Multi-Agent Systems via Communication Attacks
  6. 2026Insider Attacks in Multi-Agent LLM Consensus Systems
  7. 2026Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
  8. 2026MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability