Self-Evolving Scientific Agent Designs Physically-Reasoned Whitebox Fluid Control

[2606.08405] Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control Skip to main content Search Submit Donate Log in Computer Science > Artificial Intelligence arXiv:2606.08405 (cs) [Submitted on 7 Jun 2026 ( v1 ), last revised 9 Sep 2026 (this version, v4)] Title: Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control Authors: Boai Sun , Wenjin Guo , Zongmin Yu , Liu Yang View PDF HTML (experimental) Abstract: While neural networks excel in autonomous control, their black-box nature makes control decisions difficult to interpret and diagnose in dynamic fluids. Here, we show how self-evolving scientific agents can design explicit, neural-network-free white-box controllers by iteratively interpreting simulation evidence, accumulating control knowledge and refining controller code. We demonstrate this approach on an underactuated two-joint swimmer navigating unsteady flows via joint angular accelerations. Starting from a target-blind propulsive controller, the agent gradually constructs key mechanisms, including travelling-wave propulsion, body-frame guidance, phase-selective steering, redirect bursts and adaptive relief. The resulting controllers reach targets and generalize across changes in target position, wake geometry, cylinder count, and inflow speed without revision. Moreover, 2D control priors transfer successfully to accelerate 3D adaptation. Our work demonstrates that self-evolving agents can autonomously design physically reasoned and generalizable white-box fluid control, showing a promising paradigm beyond traditional reinforcement learning and black-box neural network control. Subjects: Artificial Intelligence (cs.AI) ; Fluid Dynamics (physics.flu-dyn) Cite as: arXiv:2606.08405 [cs.AI] (or arXiv:2606.08405v4 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2606.08405 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Boai Sun [ view email ] [v1] Sun, 7 Jun 2026 01:59:11 UTC (9,244 KB) [v2] Sun, 23 Aug 2026 14:37:35 UTC (7,451 KB) [v3] Tue, 25 Aug 2026 02:41:19 UTC (7,451 KB) [v4] Wed, 9 Sep 2026 13:41:14 UTC (6,991 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.AI < prev | next > new | recent | 2026-06 Change to browse by: cs physics physics.flu-dyn References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation 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? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Self-Evolving Scientific Agent Designs Physically-Reasoned Whitebox Fluid Control#670626
• Weather and Climate Without Fluid Mechanics#1104788
• Is it Really so Easy to Model Biological Evolution in Terms of Design-free Cumulative Selection?#761922
• The Universe, Consciousness, and Free Will: An Integrated Framework of Information, Self-Organization, and Universal Balance#74181
• Mathematical Readiness, Engagement Profiling, and the Illusion of Competence: A Quasi-Experimental Study of AI Adaptive Learning in Physics#338989