Metraipolis › archive › dc_d025b623cd2d

Absorbing State Phase Transitions in Multi-Agent Search — arXiv:2609.38327

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38327
License (as archived): CC0-1.0
Archived: 2026-10-07T12:39:29.009Z
SHA-256 of the archived text: 0f3ce7990ba2e18d9cee0086523ce84d7551b76c51c19a36aa717f084f451e86
Stable URL of this page: https://metraipolis.com/documento/dc_d025b623cd2d

How to cite

Absorbing State Phase Transitions in Multi-Agent Search — arXiv:2609.38327 — arXiv (en), https://arxiv.org/abs/2609.38327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d025b623cd2d (Metraipolis archive dc_d025b623cd2d, sha256 0f3ce7990ba2e18d9cee0086523ce84d7551b76c51c19a36aa717f084f451e86)

BibTeX

@misc{dcd025b623cd2d,
  title = {Absorbing State Phase Transitions in Multi-Agent Search — arXiv:2609.38327},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38327},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d025b623cd2d; sha256 0f3ce7990ba2e18d9cee0086523ce84d7551b76c51c19a36aa717f084f451e86},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Nontrivial dynamics can emerge in large language model (LLM)-based multi-agent systems, and preliminary evidence exists that formalisms from statistical mechanics can be effective at modeling and predicting such behaviors. In parallel, designing multi-agent communication topology for optimal task-solving is an active research question. In this paper, we focus on predicting the success of multi-agent search tasks using the formalism of absorbing state phase transitions. We first taxonomize search tasks into four types, informed by classical results in combinatorial search. We then theoretically derive a critical communication degree $d_c$, the minimum number of agents each agent can communicate with, above which incorrect hypotheses do not proliferate uncontrollably and the search enters the solved state. Finally, we evaluate frontier LLM-based multi-agent systems on real-world search and discovery tasks, software configuration debugging and physical mechanism discovery, and find that agreement with theory is mixed. LLM agents may not communicate with their neighbors and can develop strategies that are individually beneficial but limits the benefits of collaboration.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.38327 — 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 2026-10-07T12:12:18.616Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).