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

arXiv: https://arxiv.org/abs/2602.03688 · HTML: https://mlsanity.com/paper/2602.03688/

## Key facts

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

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 34)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks](https://mlsanity.com/paper/2410.11782/) (2024)
- [Learning to Schedule Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1902.01554/) (2019)
- [Latent Collaboration in Multi-Agent Systems](https://mlsanity.com/paper/2511.20639/) (2025)
- [G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems](https://mlsanity.com/paper/2502.11127/) (2025)
- [ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind](https://mlsanity.com/paper/2111.09189/) (2021)
- [SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning](https://mlsanity.com/paper/2502.04780/) (2025)
- [BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks](https://mlsanity.com/paper/2508.08127/) (2025)
- [ChatLLM Network: More brains, More intelligence](https://mlsanity.com/paper/2304.12998/) (2023)
- [LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models](https://mlsanity.com/paper/2501.05464/) (2024)
- [Adaptive Graph Pruning for Multi-Agent Communication](https://mlsanity.com/paper/2506.02951/) (2025)
- [Learning Structured Communication for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2002.04235/) (2020)

## Built on by (most cited first, 5 of 5)

- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer](https://mlsanity.com/paper/2605.17361/) (2026)
- [Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning](https://mlsanity.com/paper/2605.28433/) (2026)
- [Reinforcement Learning of Communication in a Mesh of Small Language Models](https://mlsanity.com/paper/2609.30578/) (2026)

## 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.