Metraipolis › archive › dc_03dee8862275
Cheap Talk Stabilizes Strategic Interaction in LLM Agents — arXiv:2609.16270
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16270
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:31:13.073Z
- SHA-256 of the archived text
b02505506fdc1eed3d6a09304a51e5157255a54352c8a70b4ed6c3fc7e95b64d- Stable URL of this page
https://metraipolis.com/documento/dc_03dee8862275
How to cite
Cheap Talk Stabilizes Strategic Interaction in LLM Agents — arXiv:2609.16270 — arXiv (en), https://arxiv.org/abs/2609.16270 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_03dee8862275 (Metraipolis archive dc_03dee8862275, sha256 b02505506fdc1eed3d6a09304a51e5157255a54352c8a70b4ed6c3fc7e95b64d)
BibTeX
@misc{dc03dee8862275,
title = {Cheap Talk Stabilizes Strategic Interaction in LLM Agents — arXiv:2609.16270},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16270},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_03dee8862275; sha256 b02505506fdc1eed3d6a09304a51e5157255a54352c8a70b4ed6c3fc7e95b64d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16270. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are increasingly deployed as interacting agents, making the persistence of their action policies across repeated interaction critical for reliable multi-agent operation. We investigate whether and how agent-generated, non-binding pre-play communication ("cheap talk") increases such persistence in four open-weight 7-9B-parameter LLMs. Our experiments span four repeated two-player games -- Prisoner's Dilemma, Snowdrift, Stag Hunt, and Harmony -- with incentive structures ranging from strategic conflict to alignment, each presented in six contexts. We observe unstable trajectories in all four games, although their prevalence and magnitude depend strongly on model and context. Across models, games, and contexts, cheap talk is predominantly stabilizing, with five corrected reversals concentrated in social or team framings; effects vary substantially by model and context. Controlled current-message interventions identify two separable output-level channels in Qwen: reduced action uncertainty and less between-round drift in action probabilities. Matched history-by-message counterfactuals further show that recent partner behavior conditions how mutual-benefit versus self-prioritizing language affects policy persistence. Finally, in Prisoner's Dilemma, we identify in Qwen and Falcon a history-balanced policy-content direction in late transformer layers; projecting out this direction increases realized switching during closed-loop play, demonstrating that complete trajectories are causally sensitive to this component. Together, these findings show that cheap talk can make individual trajectories more persistent across diverse incentive structures, while revealing that the magnitude and mechanisms of stabilization are model- and history-dependent.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.16270 — 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 2026-10-15T18:00:46.626Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).