# Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control

arXiv: https://arxiv.org/abs/2606.08405 · HTML: https://mlsanity.com/paper/2606.08405/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Machine Learning for Fluid Mechanics](https://mlsanity.com/paper/1905.11075/) (2019)
- [Efficient collective swimming by harnessing vortices through deep reinforcement learning](https://mlsanity.com/paper/1802.02674/) (2018)
- [A Survey on Physics Informed Reinforcement Learning: Review and Open Problems](https://mlsanity.com/paper/2309.01909/) (2023)
- [PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs](https://mlsanity.com/paper/2502.00963/) (2025)
- [ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise](https://mlsanity.com/paper/2410.19811/) (2024)
- [Synthesizing Interpretable Control Policies through Large Language Model Guided Search](https://mlsanity.com/paper/2410.05406/) (2024)
- [Enhancing Efficiency and Propulsion in Bio-mimetic Robotic Fish through End-to-End Deep Reinforcement Learning](https://mlsanity.com/paper/2506.04627/) (2025)
- [Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis](https://mlsanity.com/paper/2510.00373/) (2025)
- [Evolving Ensemble of Agents](https://mlsanity.com/paper/2605.09018/) (2026)

## Built on by (most cited first, 4 of 4)

- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [Agentic Symbolic Search: Characterizing PDEs Beyond Hand-crafted Expressions, Meshes, and Neural Networks](https://mlsanity.com/paper/2606.20467/) (2026)
- [Large language models for partial differential equation workflows](https://mlsanity.com/paper/2608.03600/) (2026)
- [SeisEvo: Evolution of Seismic Data Reconstruction Algorithms by Agents](https://mlsanity.com/paper/2608.18272/) (2026)

## Abstract (arXiv)

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.