Metraipolis › archive › dc_ec767dbce497

Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia — arXiv:2610.05041

Source
arXiv
Original
https://arxiv.org/abs/2610.05041
License (as archived)
CC0-1.0
Archived
2026-10-06T05:23:51.252Z
SHA-256 of the archived text
8e15f81756a1dca9fd144b1662ff7d1454bb9969743bd14f409c1dbc94ab3c26
Stable URL of this page
https://metraipolis.com/documento/dc_ec767dbce497

How to cite

Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia — arXiv:2610.05041 — arXiv, https://arxiv.org/abs/2610.05041 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec767dbce497 (Metraipolis archive dc_ec767dbce497, sha256 8e15f81756a1dca9fd144b1662ff7d1454bb9969743bd14f409c1dbc94ab3c26)
BibTeX
@misc{dcec767dbce497,
  title = {Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia — arXiv:2610.05041},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05041},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec767dbce497; sha256 8e15f81756a1dca9fd144b1662ff7d1454bb9969743bd14f409c1dbc94ab3c26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05041. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When does communication help a group identify hidden adversaries, and how does its value change as the group adapts? In Mafia, an informed minority hides inside an uninformed majority whose only evidence is open play. The zero-information game, where each day's vote eliminates a random player, is exactly solved and scores every society; matched-casting comparisons between protocols identify the effect of communication. Societies of 8-100 claude-haiku-4-5 agents (7,416 analyzed games, 1.9M model calls) adapt by rewriting and inheriting private strategy notes. Simultaneous broadcast improves adversary identification over silence in all nine compositions tested (8-46 players). Turn-taking removes most of this advantage; its voting landslides are as frequent as broadcast's but land on mafia near chance (1.08x versus 2.53x). At 70 players, agents reading eight statements per day identify adversaries worse than silent ones, and limited talk is worth less than at 46 players. Adaptation is fast but need not help. In their first broadcast games, citizens announce their role far more often than mafia (91% vs. 30%) and first-day votes find mafia at three times chance; within two generations citizens stop announcing and the cue fades, a change the inherited notes carry. In controlled redeployments at 16 players, societies carrying sixty generations of their own notes score below societies with none. Communication shapes both collective inference and the signals it depends on, so a protocol's value must be measured together with the adaptation that changes those signals.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.05041 — 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 2026-10-06T05:23:50.203Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).