Metraipolis › archive › dc_262111dec2d3
Emergent Collusion in Long-Horizon LLM Agent Interaction — arXiv:2609.24967
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24967
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:50:44.311Z
- SHA-256 of the archived text
067a2a63f4c6017e1a2c660068cb0b98fbc204be4c65fd942a3dfe417ea50898- Stable URL of this page
https://metraipolis.com/documento/dc_262111dec2d3
How to cite
Emergent Collusion in Long-Horizon LLM Agent Interaction — arXiv:2609.24967 — arXiv (en), https://arxiv.org/abs/2609.24967 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_262111dec2d3 (Metraipolis archive dc_262111dec2d3, sha256 067a2a63f4c6017e1a2c660068cb0b98fbc204be4c65fd942a3dfe417ea50898)
BibTeX
@misc{dc262111dec2d3,
title = {Emergent Collusion in Long-Horizon LLM Agent Interaction — arXiv:2609.24967},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24967},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_262111dec2d3; sha256 067a2a63f4c6017e1a2c660068cb0b98fbc204be4c65fd942a3dfe417ea50898},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24967. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agents repeatedly complete individual tasks, share task logs, verify each other's work, and receive rewards. We introduce realistic constraints under which higher reward is attainable only by violating the verification protocol, and find that agents increasingly deviate from the protocol over repeated interactions. Collusion emerges in 94% of trajectories across 10 models, and more capable models within the same family reach it earlier. Controlled peer interventions show that collusion is shaped by peer behavior, while ablations reveal additional effects of the verification feedback agents receive, their interaction history, and the reward structure. In particular, restricting the amount and scope of interaction history available to agents reduces collusion. Overall, our findings show that long-horizon interaction can reshape how agents coordinate in ways that create safety risks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.24967 — 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 2026-10-09T06:48:45.157Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).