Machine Collective Intelligence for Explainable Scientific Discovery

arXiv cs.AI / 5/1/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes “machine collective intelligence,” a paradigm that combines symbolic reasoning with metaheuristics to autonomously evolve explainable governing equations from observations.
It uses multiple coordinated reasoning agents to generate, evaluate, critique, and consolidate symbolic hypotheses, moving beyond single-agent inference for scientific discovery.
Experiments across deterministic, stochastic, and previously unknown dynamical systems show that the approach can recover underlying governing equations without hand-crafted domain knowledge.
The authors report major improvements in extrapolation accuracy—up to six orders of magnitude versus deep neural networks—while compressing models from roughly 0.5–1 million parameters down to 5–40 interpretable parameters.

Abstract

Deriving governing equations from empirical observations is a longstanding challenge in science. Although artificial intelligence (AI) has demonstrated substantial capabilities in function approximation, the discovery of explainable and extrapolatable equations remains a fundamental limitation of modern AI, posing a central bottleneck for AI-driven scientific discovery. Here, we present machine collective intelligence, a unified paradigm that integrates two fundamental yet distinct traditions in computational intelligence--symbolism and metaheuristics--to enable autonomous and evolutionary discovery of governing equations. It orchestrates multiple reasoning agents to evolve their symbolic hypotheses through coordinated generation, evaluation, critique, and consolidation, enabling scientific discovery beyond single-agent inference. Across scientific systems governed by deterministic, stochastic, or previously uncharacterized dynamics, machine collective intelligence autonomously recovered the underlying governing equations without relying on hand-crafted domain knowledge. Furthermore, the resulting equations reduced extrapolation error by up to six orders of magnitude relative to deep neural networks, while condensing 0.5-1 million model parameters into just 5-40 interpretable parameters. This study marks an important shift in AI toward the autonomous discovery of principled scientific equations.