# Scheming Ability in LLM-to-LLM Strategic Interactions

arXiv: https://arxiv.org/abs/2510.12826 · HTML: https://mlsanity.com/paper/2510.12826/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 30 of 32)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [Red-Teaming LLM Multi-Agent Systems via Communication Attacks](https://mlsanity.com/paper/2502.14847/) (2025)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [Scheming AIs: Will AIs fake alignment during training in order to get power?](https://mlsanity.com/paper/2311.08379/) (2023)
- [How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions](https://mlsanity.com/paper/2309.15840/) (2023)
- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Perfectly Secure Steganography Using Minimum Entropy Coupling](https://mlsanity.com/paper/2210.14889/) (2022)
- [Characterizing Manipulation from AI Systems](https://mlsanity.com/paper/2303.09387/) (2023)
- [Towards evaluations-based safety cases for AI scheming](https://mlsanity.com/paper/2411.03336/) (2024)
- [Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols](https://mlsanity.com/paper/2409.07985/) (2024)
- [Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models](https://mlsanity.com/paper/2503.01829/) (2025)
- [LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models](https://mlsanity.com/paper/2504.10430/) (2025)
- [Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language](https://mlsanity.com/paper/2507.03409/) (2025)
- [Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions](https://mlsanity.com/paper/2411.04578/) (2024)
- [AI Testing Should Account for Sophisticated Strategic Behaviour](https://mlsanity.com/paper/2508.14927/) (2025)
- [Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective](https://mlsanity.com/paper/2106.05402/) (2021)
- [Modelling Strategic Deceptive Planning in Adversarial Multi-Agent Systems](https://mlsanity.com/paper/2109.03092/) (2021)

## Built on by (most cited first, 5 of 5)

- [Evaluating and Understanding Scheming Propensity in LLM Agents](https://mlsanity.com/paper/2603.01608/) (2026)
- [Multi-Agent Systems Should be Treated as Principal-Agent Problems](https://mlsanity.com/paper/2601.23211/) (2026)
- [Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation](https://mlsanity.com/paper/2607.15434/) (2026)
- [Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI](https://mlsanity.com/paper/2603.13244/) (2026)
- [Disentangling Models from Personas in Heterogeneous LLM Simulations](https://mlsanity.com/paper/2610.07535/) (2026)

## Abstract (arXiv)

As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers, LLM-to-LLM scheming remains underexplored. We investigate the scheming ability and propensity of frontier LLM agents through two game-theoretic frameworks: a Cheap Talk signaling game and a Peer Evaluation adversarial game. Testing four models (GPT-4o, Gemini-2.5-pro, Claude-3.7-Sonnet, and Llama-3.3-70b), we measure scheming performance with and without explicit prompting while analyzing scheming tactics through chain-of-thought reasoning. When prompted, most models, especially Gemini-2.5-pro and Claude-3.7-Sonnet, achieved near-perfect performance. Critically, models exhibited significant scheming propensity without prompting: all models chose deception over confession in Peer Evaluation (100% rate), while models choosing to scheme in Cheap Talk succeeded at 95-100% rates. These findings highlight the need for robust evaluations using high-stakes game-theoretic scenarios in multi-agent settings.