{"slug": "self-improvement-memory-enables-continual-recursive-self-improvement", "title": "Self-Improvement Memory Enables Continual Recursive Self-Improvement", "summary": "A paper submitted to arXiv on 13 Nov 2026 proposes Self-Improvement Memory (SIM), a memory mechanism for the harness optimizer rather than the task-solving policy, to support Continual Recursive Self-Improvement (CRSI) across compatible benchmarks or policy models. SIM groups edits by recurring harness problem and records their rationale, predicted and observed outcomes, and evaluation context; across four domains it beat harness-only and root-cause-only continuation in cross-dataset and pairwise cross-model comparisons. In coding, across ten independent source runs, paired continuations with SIM raised final scores by an average of 2.36 points over harness-only continuation (p=0.003).", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 13 Nov 2026]\n\n# Title:Self-Improvement Memory Enables Continual Recursive Self-Improvement\n\n[View PDF](https://arxiv.org/pdf/2611.18856)\n\n[HTML (experimental)](https://arxiv.org/html/2611.18856v1)\n\nAbstract:Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this work, we study Continual Recursive Self-Improvement (CRSI), a setting for continuing existing harness-optimization methods across compatible benchmarks or policy models. We propose Self-Improvement Memory (SIM) for the harness optimizer, rather than the task-solving policy. SIM groups edits by recurring harness problem and records their rationale, predicted and observed outcomes, and evaluation context. New attempts extend this history as optimization continues. In our experiments across four domains, SIM achieves higher final scores than harness-only and root-cause-only continuation in cross-dataset and pairwise cross-model comparisons. Across ten independent source runs in coding, paired continuations with SIM improve final scores by an average of 2.36 points over harness-only continuation ($p=0.003$).\n    \n\n### Additional Features\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/))\n# 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))\n# 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))\n# 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/self-improvement-memory-enables-continual-recursive-self-improvement", "canonical_source": "https://arxiv.org/abs/2611.18856", "published_at": "2026-11-17 20:54:25+00:00", "updated_at": "2026-11-17 21:21:21.369534+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "artificial-intelligence", "ai-agents"], "entities": ["arXiv", "Self-Improvement Memory", "Continual Recursive Self-Improvement"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/self-improvement-memory-enables-continual-recursive-self-improvement", "markdown": "https://wpnews.pro/news/self-improvement-memory-enables-continual-recursive-self-improvement.md", "text": "https://wpnews.pro/news/self-improvement-memory-enables-continual-recursive-self-improvement.txt", "jsonld": "https://wpnews.pro/news/self-improvement-memory-enables-continual-recursive-self-improvement.jsonld"}}