Metraipolis › archive › dc_cb689b106f5d

Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate — arXiv:2609.27150

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27150
License (as archived)
CC0-1.0
Archived
2026-10-08T09:11:07.677Z
SHA-256 of the archived text
fd03ee1b58d6523665774120d44920be013c47ec9a17e04554f0e0c066c2ab79
Stable URL of this page
https://metraipolis.com/documento/dc_cb689b106f5d

How to cite

Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate — arXiv:2609.27150 — arXiv (en), https://arxiv.org/abs/2609.27150 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb689b106f5d (Metraipolis archive dc_cb689b106f5d, sha256 fd03ee1b58d6523665774120d44920be013c47ec9a17e04554f0e0c066c2ab79)
BibTeX
@misc{dccb689b106f5d,
  title = {Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate — arXiv:2609.27150},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27150},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb689b106f5d; sha256 fd03ee1b58d6523665774120d44920be013c47ec9a17e04554f0e0c066c2ab79},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27150. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent debate (MAD) has emerged as a promising paradigm for improving the reasoning accuracy of large language models (LLMs) through iterative peer interaction. Communication topology plays a central role in this process, motivating increasingly sophisticated mechanisms that learn, adapt, or dynamically reconfigure agent interactions to improve accuracy or reasoning reliability. Meanwhile, prior studies suggest that much simpler sparse communication can already achieve competitive performance at substantially lower cost. In this work, we take a closer look at sparse MAD and ask whether complex topology control is actually necessary to improve collective reasoning. We find that a simple random-without-replacement routing policy, which lets each agent debate with two distinct and newly sampled peers at every round, provides a surprisingly strong baseline and consistently improves the accuracy-cost trade-off of sparse MAD. Building on this observation, we further study deliberation stopping and show that lightweight stopping can substantially reduce inference cost while preserving competitive accuracy. Our results suggest that sophisticated topology control such as learned topology adaption should be evaluated against strong simple routing and stopping baselines before its additional complexity is justified.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.27150 — 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 2026-10-08T08:13:26.473Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).