[2608.20055] EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Cryptography and Security

arXiv:2608.20055 (cs)

[Submitted on 20 Aug 2026]

Title:EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models

Authors:Yiting Qu, Ziqing Yang, Chi Cui, Ye Leng, Junjie Chu, Yang Zhang<br>View a PDF of the paper titled EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models, by Yiting Qu and Ziqing Yang and Chi Cui and Ye Leng and Junjie Chu and Yang Zhang

View PDF<br>HTML (experimental)

Abstract: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.

Subjects:

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2608.20055 [cs.CR]

(or<br>arXiv:2608.20055v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2608.20055

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Yiting Qu [view email]<br>[v1]<br>Thu, 20 Aug 2026 13:52:07 UTC (2,194 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models, by Yiting Qu and Ziqing Yang and Chi Cui and Ye Leng and Junjie Chu and Yang Zhang<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CR

next >

new<br>recent<br>| 2026-08

Change to browse by:

cs<br>cs.AI

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both 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.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from