{"slug": "sciencebuddy-recursive-in-recursive-self-improvement-for-interactive-scientific", "title": "ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents", "summary": "Researchers released ScienceBuddy, an interactive scientific research workspace built on a paradigm they call recursive-in-recursive self-improvement, submitted to arXiv on 15 Sep 2026. The system couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the model under the improved harness. Benchmark cases span four scientific task families, and the team released ScienceBuddy as a research product with a website at science-buddy.io.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 15 Sep 2026]\n\n# Title:ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents\n\n[View PDF](http://arxiv.org/pdf/2609.17523v1)\n\n[HTML (experimental)](https://arxiv.org/html/2609.17523v1)\n\nAbstract:We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying out scientific tasks while transforming their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, a paradigm that couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the model under the improved harness. Harness evolution shapes training experience, and model learning creates new opportunities for harness adaptation. We present case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families. By releasing ScienceBuddy as a research product, we make this paradigm available to the scientific community and take a step toward discovery intelligence: scientific AI that advances through sustained collaboration with researchers and evolves alongside the research it supports. Website: [this http URL](http://science-buddy.io)\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))\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/sciencebuddy-recursive-in-recursive-self-improvement-for-interactive-scientific", "canonical_source": "http://arxiv.org/abs/2609.17523v1", "published_at": "2026-09-16 14:21:45+00:00", "updated_at": "2026-09-16 14:42:25.140242+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "ai-tools", "machine-learning"], "entities": ["ScienceBuddy", "arXiv", "science-buddy.io"], "alternates": {"html": "https://wpnews.pro/news/sciencebuddy-recursive-in-recursive-self-improvement-for-interactive-scientific", "markdown": "https://wpnews.pro/news/sciencebuddy-recursive-in-recursive-self-improvement-for-interactive-scientific.md", "text": "https://wpnews.pro/news/sciencebuddy-recursive-in-recursive-self-improvement-for-interactive-scientific.txt", "jsonld": "https://wpnews.pro/news/sciencebuddy-recursive-in-recursive-self-improvement-for-interactive-scientific.jsonld"}}