Metraipolis › archive › dc_7e82390df6c8
HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS — arXiv:2608.04634
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04634
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:11:32.003Z
- SHA-256 of the archived text
0aea57a1b8efabdb8bf14a16f7cf46217761cf4f611e2388260fda9254ab8e7e- Stable URL of this page
https://metraipolis.com/documento/dc_7e82390df6c8
How to cite
HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS — arXiv:2608.04634 — arXiv (en), https://arxiv.org/abs/2608.04634 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e82390df6c8 (Metraipolis archive dc_7e82390df6c8, sha256 0aea57a1b8efabdb8bf14a16f7cf46217761cf4f611e2388260fda9254ab8e7e)
BibTeX
@misc{dc7e82390df6c8,
title = {HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS — arXiv:2608.04634},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04634},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e82390df6c8; sha256 0aea57a1b8efabdb8bf14a16f7cf46217761cf4f611e2388260fda9254ab8e7e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04634. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-based multi-agent systems (MAS) typically optimize a single topology, restricting reasoning to a narrow trajectory and limiting comprehensive analytical capacity. Naively merging multiple topologies into a composite graph introduces redundant noise propagation across irrelevant connections, degrading solution quality. To address this dilemma, we propose \textbf{Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS (HELENA)}, a multi-agent framework that balances diverse reasoning paths with sparse task-dependent execution. \helena{} constructs a union MAS graph from complementary candidate topologies selected via Monte Carlo Tree Search and Determinantal Point Process, broadening the reasoning trajectory for comprehensive analysis of complex problems. A Hierarchical Sparse Coordination module then activates only a sparse subgraph at each step while agents exchange compressed latent briefs to suppress redundant noise propagation. Finally, a Local Self-Refinement stage identifies decision units with discrepancy evidence and rewrites them only when contrastive evidence simultaneously confirms a reliable solution-side failure and a challenger-side improvement. Experiments across eight benchmarks show that \helena{} achieves state-of-the-art results on all benchmarks, with an average gain of \pctup{3.47} over the strongest baseline and up to \pctup{10.34} on MMLU-Pro, achieving larger improvements on harder benchmarks at a reasonable additional cost.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.04634 — 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 2026-10-31T11:00:35.633Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).