AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework

TL;DR

This paper introduces a Bayesian adversarial multi-agent low-code platform that enhances scientific code generation by improving reliability, reducing error propagation, and streamlining human-AI collaboration in complex scientific tasks.

Contribution

The paper presents a novel Bayesian adversarial multi-agent framework integrated into a low-code platform for AI for Science, addressing reliability and evaluation challenges in scientific code generation.

Findings

Demonstrates improved code robustness and reduced error propagation.

Outperforms existing models on Earth Science tasks.

Effectively translates non-expert prompts into domain-specific requirements.

Abstract

Large Language Models (LLMs) demonstrate potentials for automating scientific code generation but face challenges in reliability, error propagation in multi-agent workflows, and evaluation in domains with ill-defined success metrics. We present a Bayesian adversarial multi-agent framework specifically designed for AI for Science (AI4S) tasks in the form of a Low-code Platform (LCP). Three LLM-based agents are coordinated under the Bayesian framework: a Task Manager that structures user inputs into actionable plans and adaptive test cases, a Code Generator that produces candidate solutions, and an Evaluator providing comprehensive feedback. The framework employs an adversarial loop where the Task Manager iteratively refines test cases to challenge the Code Generator, while prompt distributions are dynamically updated using Bayesian principles by integrating code quality metrics: functional correctness, structural alignment, and static analysis. This co-optimization of tests and code reduces dependence on LLM reliability and addresses evaluation uncertainty inherent to scientific tasks. LCP also streamlines human-AI collaboration by translating non-expert prompts into domain-specific requirements, bypassing the need for manual prompt engineering by practitioners without coding backgrounds. Benchmark evaluations demonstrate LCP's effectiveness in generating robust code while minimizing error propagation. The proposed platform is also tested on an Earth Science cross-disciplinary task and demonstrates strong reliability, outperforming competing models.