{"slug": "rl-contributes-to-illegible-reasoning-traces-in-hard-problems", "title": "RL Contributes to Illegible Reasoning Traces in Hard Problems", "summary": "A study of 14 reasoning models found that outcome-based reinforcement learning (RL) often produces illegible chain-of-thought (CoT) reasoning, with accuracy dropping by 53% when models are forced to use only legible portions, and legibility degrading on harder questions. The researchers, who submitted the paper to arXiv on 31 Oct 2025, found no correlation between legibility and performance when resampling, suggesting the relationship is nuanced, and they propose hypotheses including steganography, training artifacts, and vestigial tokens. The findings indicate that without explicit optimization for legibility, RL naturally yields models with increasingly opaque reasoning, potentially undermining monitoring approaches.", "body_md": "# Computer Science > Machine Learning\n\n[Submitted on 31 Oct 2025]\n\n# Title:Reasoning Models Sometimes Output Illegible Chains of Thought\n\n[View PDF](/pdf/2510.27338)\n\n[HTML (experimental)](https://arxiv.org/html/2510.27338v1)\n\nAbstract:Language models trained via outcome-based reinforcement learning (RL) to reason using chain-of-thought (CoT) have shown remarkable performance. Monitoring such a model's CoT may allow us to understand its intentions and detect potential malicious behavior. However, to be effective, this requires that CoTs are legible and faithful. We study CoT legibility across 14 reasoning models, finding that RL often causes reasoning to become illegible to both humans and AI monitors, with reasoning models (except Claude) generating illegible CoTs while returning to perfectly readable final answers. We show that models use illegible reasoning to reach correct answers (accuracy dropping by 53\\% when forced to use only legible portions), yet find no correlation between legibility and performance when resampling - suggesting the relationship is more nuanced. We also find that legibility degrades on harder questions. We discuss potential hypotheses for these results, including steganography, training artifacts, and vestigial tokens. These results suggest that without explicit optimization for legibility, outcome-based RL naturally produces models with increasingly opaque reasoning processes, potentially undermining monitoring approaches.\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))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))# 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/rl-contributes-to-illegible-reasoning-traces-in-hard-problems", "canonical_source": "https://arxiv.org/abs/2510.27338", "published_at": "2026-08-26 02:42:57+00:00", "updated_at": "2026-08-26 03:14:05.822980+00:00", "lang": "en", "topics": ["machine-learning", "ai-safety", "ai-research"], "entities": ["arXiv", "Claude"], "alternates": {"html": "https://wpnews.pro/news/rl-contributes-to-illegible-reasoning-traces-in-hard-problems", "markdown": "https://wpnews.pro/news/rl-contributes-to-illegible-reasoning-traces-in-hard-problems.md", "text": "https://wpnews.pro/news/rl-contributes-to-illegible-reasoning-traces-in-hard-problems.txt", "jsonld": "https://wpnews.pro/news/rl-contributes-to-illegible-reasoning-traces-in-hard-problems.jsonld"}}