Voluntary Collusion with Secret Tools in Competing LLM Agents

Computer Science > Artificial Intelligence [Submitted on 26 May 2026] Voluntary Collusion with Secret Tools in Competing LLM Agents Xijie Zeng, Frank Rudzicz Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate this phenomenon, we introduce an empirical framework built on two strategic multi-agent environments: Liar's Bar, a competitive deception scenario, and Cleanup, a mixed-motive resource-management scenario, in which agents are offered secret collusion tools that provide significant advantages while clearly disadvantaging the other agents. Across 12 models (at the 7B, 70B, and proprietary scales) and 6 prompt variants, we find that most agents consistently accept these tools and develop collusive strategies, while explicitly acknowledging the unfairness of the tools before accepting. We further show that neither the unfairness labels nor baseline alignment alone reliably deters collusion: only explicit ethical framing reduces adoption and, even then, smaller models remain susceptible. More broadly, our work presents the first systematic investigation of voluntary collusion adoption in LLM-based multi-agent systems, and suggests that preventing such behaviour requires explicit safeguards rather than reliance on general alignment. Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) Cite as: arXiv:2605.27593 [cs.AI]   (or arXiv:2605.27593v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.27593 Focus to learn more Submission history From: Xijie Zeng [view email] [v1] Tue, 26 May 2026 19:06:39 UTC (9,029 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.MA References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)