Metraipolis › archive › dc_b849f1f8317d

Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation — arXiv:2608.12125

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12125
License (as archived): CC0-1.0
Archived: 2026-10-19T05:14:48.916Z
SHA-256 of the archived text: ce3efc630b19f01079f40e6f9cde4dbc4f8fd29bd8abf7e55dc3bc270f256cf3
Stable URL of this page: https://metraipolis.com/documento/dc_b849f1f8317d

How to cite

Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation — arXiv:2608.12125 — arXiv (en), https://arxiv.org/abs/2608.12125 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b849f1f8317d (Metraipolis archive dc_b849f1f8317d, sha256 ce3efc630b19f01079f40e6f9cde4dbc4f8fd29bd8abf7e55dc3bc270f256cf3)

BibTeX

@misc{dcb849f1f8317d,
  title = {Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation — arXiv:2608.12125},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12125},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b849f1f8317d; sha256 ce3efc630b19f01079f40e6f9cde4dbc4f8fd29bd8abf7e55dc3bc270f256cf3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12125. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As LLM-based agents with user-instructed goals are becoming widely deployed, they increasingly encounter each other in strategic interactions, and face challenges of finding mutually beneficial outcomes. Prior literature has argued that cooperation problems such as the Prisoner's Dilemma are resolvable in settings where agents know they follow very similar decision making patterns, as for example in monocultural AI ecosystems. Following that line of work, this paper introduces the first framework for evaluating LLM decision making when agents are provided with graded similarity signals. Among our findings, we establish that different LLM models vary drastically in how they navigate similarity signals, with some modern models showing consistent behavior across cooperation problems, payoff structures, and prompt framing. Perhaps surprisingly, our experiments also show that the dataset based on which the similarity signal is computed has small to no impact on induced cooperation, and that LLM models systematically self-identify as highly similar when asked to evaluate another model's chain-of-thought reasoning by themselves. Finally, we develop an LLM-behavioral-game-theoretic model that captures some of their reasoning rationale, and show that it can support cooperative outcomes in equilibrium under sufficiently high similarity scores.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.MA).
Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.12125 — 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 2026-10-19T05:08:22.844Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).