# Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games

arXiv: https://arxiv.org/abs/2605.14283 · HTML: https://mlsanity.com/paper/2605.14283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 10 of 10)

- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Watermarking Makes Language Models Radioactive](https://mlsanity.com/paper/2402.14904/) (2024)
- [Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models](https://mlsanity.com/paper/2402.18059/) (2024)
- [PostMark: A Robust Blackbox Watermark for Large Language Models](https://mlsanity.com/paper/2406.14517/) (2024)
- [BotSim: LLM-Powered Malicious Social Botnet Simulation](https://mlsanity.com/paper/2412.13420/) (2024)
- [Necessary and Sufficient Watermark for Large Language Models](https://mlsanity.com/paper/2310.00833/) (2023)
- [General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess](https://mlsanity.com/paper/2506.01242/) (2025)
- [Steganography in Game Actions](https://mlsanity.com/paper/2412.10442/) (2024)
- [Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization](https://mlsanity.com/paper/2510.15976/) (2025)

## Abstract (arXiv)

Watermarking techniques for large language models (LLMs), which encode hidden information in the output so its source can be verified, have gained significant attention in recent days, thanks to their potential capability to detect accidental or deliberate misuse. Similar challenges involving model misuse also exist in the context of game-playing, such as when detecting the unauthorized use of AI tools in gaming platforms (e.g., cheating in online chess). In this paper, we initiate the study of how game-playing strategies can be watermarked. We show how the KGW watermark for LLMs can be adapted to watermark game-playing agents in perfect-information extensive-form games. The watermark can then be detected using a statistical test. We show that the degradation in the quality of the watermarked strategy profile, quantified by the expected utility, can be bounded, but there is a tradeoff between detectability and quality. In our experiments, we bootstrap the watermarking framework to various chess engines and demonstrate that a) the impact of the watermark on the quality of the strategy is negligible and b) the watermark can be detected with just a handful of games.