# R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models

arXiv: https://arxiv.org/abs/2604.25247 · HTML: https://mlsanity.com/paper/2604.25247/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2304.01933/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models](https://mlsanity.com/paper/2401.12242/) (2024)
- [REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models](https://mlsanity.com/paper/2310.12362/) (2023)
- [Watermarking Text Generated by Black-Box Language Models](https://mlsanity.com/paper/2305.08883/) (2023)
- [Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark](https://mlsanity.com/paper/2305.10036/) (2023)
- [ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs](https://mlsanity.com/paper/2504.05605/) (2025)
- [PostMark: A Robust Blackbox Watermark for Large Language Models](https://mlsanity.com/paper/2406.14517/) (2024)
- [Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning](https://mlsanity.com/paper/2402.14883/) (2024)
- [A Watermark for Black-Box Language Models](https://mlsanity.com/paper/2410.02099/) (2024)
- [SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models](https://mlsanity.com/paper/2502.02787/) (2025)
- [SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation](https://mlsanity.com/paper/2412.05829/) (2024)
- [ModelShield: Adaptive and Robust Watermark against Model Extraction Attack](https://mlsanity.com/paper/2405.02365/) (2024)
- [Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2505.16367/) (2025)
- [CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems](https://mlsanity.com/paper/2505.19405/) (2025)
- [SEAL: Subspace-Anchored Watermarks for LLM Ownership](https://mlsanity.com/paper/2511.11356/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are widely deployed in multiple scenarios due to reasoning capabilities. In order to prevent the models from being misused, watermarking is generally employed to ensure ownership. However, most existing watermarking methods rely on superficial modifications to the model's output distribution, rendering the watermark vulnerable to perturbation and removal. To overcome this challenge, this paper introduces a reasoning-layer framework termed Redundant Chain-of-Thought (R-CoT), which embeds watermarks into the reasoning path. A dual-trajectory optimization mechanism based on GRPO enables the native and the watermark reasoning path to coexist within a shared parameter space, internalizing the watermark as a distinct reasoning policy. Therefore, the watermark is embedded into the model's stable reasoning path, avoiding the watermark failure caused by output-level perturbations. Experimental results show that, compared with existing methods, R-CoT achieves high watermark effectiveness and strong robustness. Under fine-tuning and other post-training operations, the true positive rate (TPR) consistently remains above 95%, exhibiting only marginal degradation.