The AI Scientific Community: Agentic Virtual Lab Swarms

Ulisses Braga-Neto

cs.AIMar 22, 2026

The AI Scientific Community: Agentic Virtual Lab Swarms

Authors: Ulisses Braga-Neto

Organizations: Department of Electrical and Computer Engineering, Texas A&M University

Abstract

In this short note we propose using agentic swarms of virtual labs as a model of an AI Science Community. In this paradigm, each particle in the swarm represents a complete virtual laboratory instance, enabling collective scientific exploration that mirrors real-world research communities. The framework leverages the inherent properties of swarm intelligence - decentralized coordination, balanced exploration-exploitation trade-offs, and emergent collective behavior - to simulate the behavior of a scientific community and potentially accelerate scientific discovery. We discuss architectural considerations, inter-laboratory communication and influence mechanisms including citation-analogous voting systems, fitness function design for quantifying scientific success, anticipated emergent behaviors, mechanisms for preventing lab dominance and preserving diversity, and computational efficiency strategies to enable large swarms exhibiting complex emergent behavior analogous to real-world scientific communities. A working instance of the AI Science Community is currently under development.

Figures & tables

Figure 1: The AI Science Community (generated with Nano Banana 2 at https://openart.ai/ ).

AI for Science

AI for Science applies machine learning and AI agents to scientific data, models, experiments, and discovery workflows.

See all 157 papers

An Agentic AI Scientific Community for Automated Neural Operator Discovery
Jul 13, 2026Luis Loo, Ulisses Braga-NetoAI Agents for Scientific Discovery LLM Agent Orchestration
Department of Electrical & Computer Engineering Texas A&M University, College Station, TX
Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery
May 6, 2026Zhenning Yang, Yuhan Chen, Patrick Tser Jern Kon +5AI for Science AI Agents for Scientific Discovery
University of Michigan
From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science
Feb 23, 2026Lukas Weidener, Marko Brkić, Phillip Lee +3Autonomous Research Agents AI Agents for Scientific Discovery

Jul 13, 2026J/K move · Enter open · S save

An Agentic AI Scientific Community for Automated Neural Operator Discovery

Luis Loo, Ulisses Braga-Neto

Department of Electrical & Computer Engineering Texas A&M University, College Station, TX

AI Agents for Scientific Discovery LLM Agent Orchestration Autonomous Scientific Discovery PDE Operator Learning Neural Architecture Search Neural Operators

Open paper AskPDF arXiv

We present an agentic approach to autonomous neural operator discovery based on an AI scientific community, which consists of a swarm of virtual laboratories that interact under a citation-based economy of influence. Highly-cited labs found new labs that follow their research direction and replace non-performing labs. Each virtual lab contains three agents: an LLM planner that proposes an architecture, a numerical worker that trains and measures it, and an LLM reviewer that participates in cross-lab peer review. All labs share a common vocabulary consisting of DeepONet (branch-trunk), Fourier, Transformer (attention), wavelet, and residual convolutional neural operator building blocks. We evaluate the neural operator AI scientific community on five problems, namely piecewise regression, the linear advection and Burgers 1D PDEs, and the Navier-Stokes and Darcy flow 2D PDEs, while repeating the simulation three times for each problem. The results show that the neural operator AI scientific community is capable of discovering high-accuracy, low-parameter-count neural operator architectures. All 9,623 LLM calls are logged and audited, which reveals that the virtual lab LLM planners choose to hybridize in 99.8% of their logged decisions, consistently returning multi-family hybrids. Moreover, we conducted an ablation study by replacing the LLM agents in each lab by rule-based alternatives, which caused the scientific community to collapse to non-hybridized single-family stacks in several cases, showing that LLM agency is needed to preserve diversity. The results suggest a no-free-lunch theorem for neural operators: there is no universal winner. The code, configurations, and the complete LLM transcripts are released at https://github.com/luislootx/AI-SC.

Abstract

AI for Science

Explore similar work

An Agentic AI Scientific Community for Automated Neural Operator Discovery

Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery

From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science