Step 6: tool results

read_page

{
  "url": "https://arxiv.org/abs/2510.19851",
  "max_chars": 3000
}

{"ok":true,"url":"https://arxiv.org/abs/2510.19851","text":"[2510.19851] Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability\nSkip to main content\nSearch\nSubmit\nDonate\nLog in\nSearch arXiv\nPress Enter to search &middot; Advanced search\n-->\nComputer Science > Cryptography and Security\narXiv:2510.19851 (cs)\n[Submitted on 21 Oct 2025]\nTitle: Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability\nAuthors: Artur Zolkowski , Wen Xing , David Lindner , Florian Tramèr , Erik Jenner\nView a PDF of the paper titled Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability, by Artur Zolkowski and 4 other authors\nView PDF\nHTML (experimental)\nAbstract: Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignment monitoring: when models articulate their reasoning faithfully, monitors can detect and mitigate harmful behaviors before undesirable outcomes occur. However, a key uncertainty is: Can models obfuscate their CoT in order to pursue hidden adversarial objectives while evading detection? To answer this question and thus stress-test CoT monitorability, we develop a composable and quantifiable taxonomy of prompts to elicit CoT obfuscation. We evaluate both internal CoT (reasoning traces) and external CoT (prompted reasoning in outputs) using toy tasks and more realistic environments in SHADE-Arena. We show that: (i) CoT monitoring performs accurately and efficiently without obfuscation pressure. (ii) Under strong obfuscation pressure, some models successfully complete adversarial tasks while evading detection. (iii) Models do not obfuscate their internal CoT as much as their external CoT (under prompt pressure). These results suggest that while CoT provides valuable oversight in benign settings, robust deployment requires model-specific stress-testing of monitorability.\nSubjects:\nCryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI)\nCite as:\narXiv:2510.19851 [cs.CR]\n(or\narXiv:2510.19851v1 [cs.CR] for this version)\nhttps://doi.org/10.48550/arXiv.2510.19851\nFocus to learn more\narXiv-issued DOI via DataCite\nSubmission history\nFrom: Wen Xing [ view email ] [v1]\nTue, 21 Oct 2025 18:07:10 UTC (425 KB)\nFull-text links:\nAccess Paper:\nView a PDF of the paper titled Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability, by Artur Zolkowski and 4 other authors\nView PDF\nHTML (experimental)\nTeX Source\nview license\nAdditional Features\nAudio Summary\nCurrent browse context:\ncs.CR\n< prev\n|\nnext >\nnew\n|\nrecent\n| 2025-10\nChange to browse by:\ncs\ncs.AI\nReferences & Citations\nSciX\nGoogle Scholar\nSemantic Scholar\nexport BibTeX citation\nLoading...\nBibTeX formatted citation\n&times;\nloading...\nData provided by:\nBookmark\nBibliographic Tools\nBibliographic and Citation Tools\nBibliographic Explorer Toggle\nBibliographic Explorer ( What is the Explorer? )\nConnected Papers Toggle\nConn","chars":3000,"total_chars":4803,"offset":0,"truncated":true,"next_offset":3000}