# CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems

arXiv: https://arxiv.org/abs/2505.19405 · HTML: https://mlsanity.com/paper/2505.19405/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 62 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples](https://mlsanity.com/paper/2305.15269/) (2023)
- [BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models](https://mlsanity.com/paper/2401.12242/) (2024)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation](https://mlsanity.com/paper/2406.12975/) (2024)
- [ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs](https://mlsanity.com/paper/2504.05605/) (2025)
- [Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning](https://mlsanity.com/paper/2402.14883/) (2024)
- [UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving](https://mlsanity.com/paper/2305.18829/) (2023)
- [Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning](https://mlsanity.com/paper/2501.19180/) (2025)
- [GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2306.04636/) (2023)
- [Can Large Vision-Language Models Detect Images Copyright Infringement from GenAI?](https://mlsanity.com/paper/2502.16618/) (2025)
- [Robust and Minimally Invasive Watermarking for EaaS](https://mlsanity.com/paper/2410.17552/) (2024)
- [A scalable approach for short-term disease forecasting in high spatial resolution areal data](https://mlsanity.com/paper/2303.16549/) (2023)

## Built on by (most cited first, 4 of 4)

- [On Protecting Agentic Systems' Intellectual Property via Watermarking](https://mlsanity.com/paper/2602.08401/) (2026)
- [Towards Provable (In)Secure Model Weight Release Schemes](https://mlsanity.com/paper/2506.19874/) (2025)
- [Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs](https://mlsanity.com/paper/2603.05618/) (2026)
- [R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models](https://mlsanity.com/paper/2604.25247/) (2026)

## Abstract (arXiv)

As large language models (LLMs) evolve into autonomous agents capable of collaborative reasoning and task execution, multi-agent LLM systems have emerged as a powerful paradigm for solving complex problems. However, these systems pose new challenges for copyright protection, particularly when sensitive or copyrighted content is inadvertently recalled through inter-agent communication and reasoning. Existing protection techniques primarily focus on detecting content in final outputs, overlooking the richer, more revealing reasoning processes within the agents themselves. In this paper, we introduce CoTGuard, a novel framework for copyright protection that leverages trigger-based detection within Chain-of-Thought (CoT) reasoning. Specifically, we can activate specific CoT segments and monitor intermediate reasoning steps for unauthorized content reproduction by embedding specific trigger queries into agent prompts. This approach enables fine-grained, interpretable detection of copyright violations in collaborative agent scenarios. We evaluate CoTGuard on various benchmarks in extensive experiments and show that it effectively uncovers content leakage with minimal interference to task performance. Our findings suggest that reasoning-level monitoring offers a promising direction for safeguarding intellectual property in LLM-based agent systems.