{"slug": "echocot-extracting-hidden-chain-of-thought-from-large-reasoning-models", "title": "EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models", "summary": "Researchers have developed EchoCoT, a multi-step attack that extracts hidden chain-of-thought (CoT) traces from black-box large reasoning models (LRMs) via API interactions, achieving up to 66.4% near-verbatim extraction success on open-source models and up to 80% on unseen datasets, and extracting 33,463 tokens from a 32,948-token target on Gemini-2.5. The study, submitted to arXiv on 20 Aug 2026, evaluated EchoCoT on three open-source and five frontier proprietary LRMs, establishing hidden-CoT extraction as a practical security risk and highlighting the need to better protect hidden CoT assets.", "body_md": "# Computer Science > Cryptography and Security\n\n[Submitted on 20 Aug 2026]\n\n# Title:EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models\n\n[View PDF](/pdf/2608.20055)\n\n[HTML (experimental)](https://arxiv.org/html/2608.20055v1)\n\nAbstract:Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be directly extracted from black-box models remains largely unexplored. In this work, we systematically study whether hidden CoTs can be extracted near-verbatim from black-box LRMs through API interactions. We identify a previously overlooked reasoning replay surface between tool calls and develop EchoCoT, a multi-step attack that iteratively extracts hidden CoTs using API-returned fidelity signals. We further develop an LLM-based optimization framework that automatically searches for an effective universal injection trajectory across various datasets. We evaluate EchoCoT on three open-source and five frontier proprietary LRMs. On open-source LRMs, EchoCoT achieves up to 66.4\\% near-verbatim extraction success, with the extracted trace length within 10\\% of the target and at least 90\\% of tokens exactly matching the target CoT. The same injection trajectory also generalizes to unseen datasets, achieving up to 80\\% extraction success under the same criterion. For tested frontier proprietary LRMs, a substantial fraction of extracted CoTs closely align with provider-reported reasoning lengths and available CoT summaries. EchoCoT can also extract very long CoTs: on Gemini-2.5, it extracts 33,463 tokens from a 32,948-token target. These results establish hidden-CoT extraction as a practical security risk and highlight the need to better protect hidden CoT assets.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/echocot-extracting-hidden-chain-of-thought-from-large-reasoning-models", "canonical_source": "https://arxiv.org/abs/2608.20055", "published_at": "2026-08-22 04:07:07+00:00", "updated_at": "2026-08-22 04:43:30.160383+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-research", "ai-policy"], "entities": ["EchoCoT", "Gemini-2.5", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/echocot-extracting-hidden-chain-of-thought-from-large-reasoning-models", "markdown": "https://wpnews.pro/news/echocot-extracting-hidden-chain-of-thought-from-large-reasoning-models.md", "text": "https://wpnews.pro/news/echocot-extracting-hidden-chain-of-thought-from-large-reasoning-models.txt", "jsonld": "https://wpnews.pro/news/echocot-extracting-hidden-chain-of-thought-from-large-reasoning-models.jsonld"}}