Metraipolis › archive › dc_7864bcaa20e2

Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling for Efficient LLM Multi-Agent Collaboration — arXiv:2610.25851

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.25851
License (as archived)
CC0-1.0
Archived
2026-10-20T08:41:48.731Z
SHA-256 of the archived text
a07f64ad291aaa18b5903485e58cc1fac7bf58b52f9011f38203a439aeb48956
Stable URL of this page
https://metraipolis.com/documento/dc_7864bcaa20e2

How to cite

Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling for Efficient LLM Multi-Agent Collaboration — arXiv:2610.25851 — arXiv (en), https://arxiv.org/abs/2610.25851 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7864bcaa20e2 (Metraipolis archive dc_7864bcaa20e2, sha256 a07f64ad291aaa18b5903485e58cc1fac7bf58b52f9011f38203a439aeb48956)
BibTeX
@misc{dc7864bcaa20e2,
  title = {Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling for Efficient LLM Multi-Agent Collaboration — arXiv:2610.25851},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.25851},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7864bcaa20e2; sha256 a07f64ad291aaa18b5903485e58cc1fac7bf58b52f9011f38203a439aeb48956},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.25851. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.25851 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-20T08:41:40.078Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).