arXiv:2606.08405v4 Announce Type: replace 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.

Peripheral serotonergic signaling has been implicated in diverse physiological processes, yet its role in coordinating glial-immune interactions remains poorly understood. In this issue of Cell, Wen and colleagues identify enteric glial cells as critical effectors of peripheral 5-HT2AR agonism, uncovering a serotonergic neuroimmune circuit that drives cytotoxic T cell-mediated immunity against colorectal cancer.