analiza aiqbench
This research introduces a self-evolving scientific agent that leverages large language models and iterative code generation to design interpretable controllers for complex physical systems. By replacing opaque weight adjustments with whitebox controller refinement, the system autonomously solves non-linear fluid-structure interaction problems while maintaining rigorous physical reasoning. The approach demonstrates how autonomous agents can transform raw simulation evidence into robust, generalizable control policies without case-specific retraining.
Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
arXiv:2606.08405v2 Announce Type: replace Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific control design in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures. Here, we present a self-evolving scientific agent workflow, driven by large language models and iterative code generation, that automates controller construction while preserving strict interpretability and rigorous physical reasoning. Instead of adjusting weights, the agent deploys candidate whitebox controllers into physical simulations, actively diagnoses dynamic behaviors from multimodal evidence, and translates these observations into progressive source-code refinements. We demonstrate this framework on a highly non-linear fluid-structure interaction problem: an underactuated, two-joint dogfish swimmer tasked with spatial target reaching in an unsteady flow using only joint angular accelerations. Starting from a target-blind propulsive seed, the agent autonomously designs and refines a unified controller that reaches a target embedded in an unsteady four-cylinder wake. Without retraining, retuning or case-specific branching, the retained controller achieves target capture across the full generalization test matrix, spanning variations in target position, rear-row geometry, cylinder count and inflow speed. The auditable evolution log reveals an emergent control architecture built upon travelling-wave propulsion, body-frame bearing guidance, phase-selective steering, corrective burst and adaptive relief. Our results show that an autonomous scientific agent can successfully transform accumulated physical evidence into a robust, mathematically readable control policy, while maintaining a fully traceable process of scientific control design.
Abstract:While data-intensive deep reinforcement learning can optimize complex control policies, scientific control design in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures. Here, we present a self-evolving scientific agent workflow, driven by large language models and iterative code generation, that automates controller construction while preserving strict interpretability and rigorous physical reasoning. Instead of adjusting weights, the agent deploys candidate whitebox controllers into physical simulations, actively diagnoses dynamic behaviors from multimodal evidence, and translates these observations into progressive source-code refinements. We demonstrate this framework on a highly non-linear fluid-structure interaction problem: an underactuated, two-joint dogfish swimmer tasked with spatial target reaching in an unsteady flow using only joint angular accelerations. Starting from a target-blind propulsive seed, the agent autonomously designs and refines a unified controller that reaches a target embedded in an unsteady four-cylinder wake. Without retraining, retuning or case-specific branching, the retained controller achieves target capture across the full generalization test matrix, spanning variations in target position, rear-row geometry, cylinder count and inflow speed. The auditable evolution log reveals an emergent control architecture built upon travelling-wave propulsion, body-frame bearing guidance, phase-selective steering, corrective burst and adaptive relief. Our results show that an autonomous scientific agent can successfully transform accumulated physical evidence into a robust, mathematically readable control policy, while maintaining a fully traceable process of scientific control design.
Artificial Intelligence (cs.AI); Fluid Dynamics (physics.flu-dyn)
arXiv:2606.08405 [cs.AI]
(or arXiv:2606.08405v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.08405 Focus to learn more arXiv-issued DOI via DataCite
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.
Text integral sub licența deschisă a publicației · 322 cuvinte
Subiecte conexe
Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
arXiv · 9 iun. 2026
Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye
Import AI · 24 aug. 2026
XtalPi Holdings Limited: XtalPi Holdings Announces 2026 Interim Results
finanznachrichten.de · 19 aug. 2026
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · 8 oct. 2026