Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control

• URL: http://arxiv.org/abs/2606.08405v1
• Date: Sun, 07 Jun 2026 01:59:11 GMT
• Title: Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
• Abstract summary: We present a self-evolving scientific-agent workflow that automates controller construction while preserving strict interpretability and rigorous physical reasoning.<n>We show that an autonomous scientific agent can successfully transform accumulated physical evidence into robust, mathematically readable control policy.
• Score: 6.923599492589765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery 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 strategies 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 using only joint angular accelerations. Starting from a propulsive seed policy that exhibits a one-sided steering bias, the agent autonomously discovers and refines a unified controller that robustly captures all canonical targets. Remarkably, without any retraining or target-specific branching, the synthesized control policy generalizes to unseen static targets and dynamically curved pursuit trajectories. The auditable evolve log reveals an emergent control architecture built upon traveling-wave propulsion, body-frame target guidance, yaw-rate feedback, signed mean-tail curvature, and adaptive cadence relief. Our results show that an autonomous scientific agent can successfully transform accumulated physical evidence into robust, mathematically readable control policy, while maintaining a fully traceable process of scientific discovery.

Related papers

• Metacognitive Steering: Learning the Structure of Scientific Judgment [0.16863755729554886]
  Long-horizon scientific discovery requires agents to alternate between exploration, disciplined execution, and critical reassessment as evidence changes.<n>Current language models are trained primarily on the products of science and optimized using outcome-level signals.<n>We investigate whether such judgment can be recovered from scientist interaction traces and used to control the internal synthesis of a frozen frontier model.
  arXiv  Detail & Related papers  (2026-09-14T19:10:03Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control [50.28263951510334]
  We propose a hybrid hierarchical control framework for reactive dexterous grasping.<n>The proposed framework explicitly decouples high-level spatial intent from low-level joint execution.<n>We extensively validate the proposed framework through a rigorous simulation-to-reality pipeline.
  arXiv  Detail & Related papers  (2026-05-05T04:49:38Z)
• Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange [3.923443951480117]
  ScienceClaw + Infinite is a framework for autonomous scientific investigation in which independent agents conduct research without central coordination.<n>The system is built around three components: an interoperable registry of over 300 scientific skills, an artifact layer that preserves full computational lineage, and a structured platform for agent-based scientific discourse.
  arXiv  Detail & Related papers  (2026-03-15T10:06:57Z)
• Data-Driven Control of a Magnetically Actuated Fish-Like Robot [2.5782420501870296]
  Magnetically actuated fish-like robots offer promising solutions for underwater exploration due to their miniaturization and agility.<n>This paper proposes a data-driven control framework to address these complexities without relying on analytical modeling.
  arXiv  Detail & Related papers  (2026-03-05T04:08:08Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery [10.217363774023033]
  OR-Agent is a multi-agent research framework designed for automated exploration in rich experimental environments.<n>We introduce an evolutionary-systematic mechanism that unifies evolutionary selection of research starting points, comprehensive research plan generation, and coordinated exploration within a research tree.<n>We conduct experiments across classical optimization benchmarks-including traveling salesman, capacitated vehicle routing, bin packing, orienteering, and multiple knapsack problems-as well as a simulation-based cooperative driving scenarios.
  arXiv  Detail & Related papers  (2026-02-14T13:32:03Z)
• Self-supervised Physics-Informed Manipulation of Deformable Linear Objects with Non-negligible Dynamics [14.801939035043352]
  SPiD is a physics-informed self-supervised learning framework for dynamic manipulation of deformable linear objects.<n>We train a neural controller using a task-oriented cost, enabling end-to-end optimization through interaction with the differentiable object model.<n>We develop an affordable markerless rope perception method and demonstrate that our controller maintains performance with noisy and low-frequency state updates.
  arXiv  Detail & Related papers  (2026-02-03T15:14:09Z)
• EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning [63.03672166010434]
  We introduce an evolutionary, task-agnostic, strategy-guided, executably-checkable data synthesis framework.<n>It jointly synthesizes problems, diverse candidate solutions, and verification artifacts.<n>It iteratively discovers strategies via a consistency-based evaluator that enforces agreement between human-annotated and strategy-induced checks.
  arXiv  Detail & Related papers  (2025-10-20T11:56:35Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion [0.0]
  We present CARL, a quadruped agent that can be controlled with high-level directives and react naturally to dynamic environments. We use Generative Adrial Networks to adapt high-level controls, such as speed and heading, to action distributions that correspond to the original animations. Further fine-tuning through the deep reinforcement learning enables the agent to recover from unseen external perturbations while producing smooth transitions.
  arXiv  Detail & Related papers  (2020-05-07T07:18:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.