{"slug": "learning-who-talks-to-whom-role-aware-communication-topology-scheduling", "title": "Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling", "summary": "A paper submitted to arXiv on 19 October 2026 proposes ACTS, a role-aware adaptive communication topology scheduling framework that lets LLM multi-agent teams dynamically decide which agents talk to each other and when. ACTS runs under a Centralized Training with Decentralized Execution (CTDE) paradigm and combines a Role-conditioned Relational Attention module with a Topological Attention Mixer that embeds the directed communication graph into team value decomposition. Across 9 benchmarks spanning code generation, multi-step reasoning, general knowledge and competitive mathematics, ACTS raised average accuracy by up to 6.19 percentage points while cutting token consumption by more than 15% versus state-of-the-art baselines.", "body_md": "# Computer Science > Multiagent Systems\n\n  [Submitted on 19 Oct 2026]\n\n# Title:Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling for Efficient LLM Multi-Agent Collaboration\n\n[View PDF](https://arxiv.org/pdf/2610.25851)\n\n[HTML (experimental)](https://arxiv.org/html/2610.25851v1)\n\nAbstract:Multi-agent systems driven by large language models (LLMs) rely on structured communication topologies to facilitate information exchange and collaborative reasoning. However, effectively scheduling these topologies to dynamically determine who talks to whom and when to communicate remains a fundamental challenge in balancing collective reasoning performance against exponential token overhead. Existing topology scheduling approaches either enforce static communication graphs that cannot adapt to dynamic problem-solving states, or overlook agent role complementarity while failing to explicitly incorporate the synthesized graph structure into team-level decision evaluation. To tackle these limitations, we propose ACTS, a role-aware adaptive communication topology scheduling framework for efficient LLM multi-agent collaboration. Orchestrated within a Centralized Training with Decentralized Execution (CTDE) paradigm, ACTS introduces a novel dual-attention mechanism. Specifically, a Role-conditioned Relational Attention module dynamically selects variable-cardinality interaction partners based on agent roles and evolving execution states, while a Topological Attention Mixer explicitly embeds the directed communication topology into team value decomposition for precise credit assignment. Comprehensive evaluations across 9 challenging benchmarks covering code generation, multi-step reasoning, general knowledge, and competitive mathematics demonstrate that ACTS consistently outperforms state-of-the-art baselines, boosting average accuracy by up to 6.19 percentage points while reducing token consumption by over 15%. The project website is available at [this https URL](https://acts-mas.github.io/ACTS/).\n    \n\n### Additional Features\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/learning-who-talks-to-whom-role-aware-communication-topology-scheduling", "canonical_source": "https://arxiv.org/abs/2610.25851", "published_at": "2026-10-20 07:32:22+00:00", "updated_at": "2026-10-20 07:47:03.808361+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "ai-research", "artificial-intelligence"], "entities": ["ACTS", "arXiv", "Centralized Training with Decentralized Execution (CTDE)", "Role-conditioned Relational Attention", "Topological Attention Mixer"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/learning-who-talks-to-whom-role-aware-communication-topology-scheduling", "markdown": "https://wpnews.pro/news/learning-who-talks-to-whom-role-aware-communication-topology-scheduling.md", "text": "https://wpnews.pro/news/learning-who-talks-to-whom-role-aware-communication-topology-scheduling.txt", "jsonld": "https://wpnews.pro/news/learning-who-talks-to-whom-role-aware-communication-topology-scheduling.jsonld"}}