Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems

2026-07-09

AI Summary

This work addresses the limitations of traditional evolutionary computation, which is confined to isolated optimization of predefined problems and struggles to support cumulative discovery in open-ended scientific inquiry. To bridge this gap, the paper proposes an Evolutionary Intelligence (EI) framework that integrates candidate solution optimization with cross-generational experience retention, thereby enabling autonomous systems capable of continuous learning and scientific discovery. The authors introduce a novel five-dimensional analytical model—encompassing evolutionary object, variation mechanism, selection criterion, feedback source, and timing of evolution—to systematically articulate the paradigm shift from optimization to discovery. Empirical evaluations demonstrate EI’s effectiveness across diverse scientific exploration scenarios, while highlighting critical future directions, including the development of robust evaluation metrics, traceable evolutionary processes, and shared infrastructural resources.

Abstract

Artificial intelligence (AI) is shifting scientific discovery from task-specific workflows towards autonomous systems that organize exploration with experimental and human feedback in open-ended candidate spaces. Evolutionary computation (EC) provides a computational basis for feedback-driven discovery because population-based search can maintain diverse scientific candidates while steering exploration through accumulated evidence. However, EC predominantly focuses on candidate refinement for predefined problems, whereas cumulative discovery requires experience retention. To bridge this gap, this review introduces evolutionary intelligence (EI) for scientific discovery. EI characterizes scientific AI systems that sustain exploration by linking candidate refinement with experience retention across evolutionary cycles. We introduce a five-dimensional analytical framework that asks what evolves, how candidates change, why candidates are selected, where feedback originates, and when evolution occurs. This framework clarifies how EI transforms isolated search trajectories into cumulative scientific insight. We further demonstrate this paradigm across diverse discovery modes, from evolving concrete scientific entities to orchestrating automated research workflows. Finally, we identify critical bottlenecks regarding evaluation, process traceability, and shared infrastructure, providing a concrete roadmap for advancing the transition from EC to EI in scientific discovery.

Problem

• evolutionary computation
• scientific discovery
• experience retention
• cumulative discovery
• evolutionary intelligence

Innovation

• Evolutionary Intelligence
• Cumulative Discovery
• Experience Retention
• Population-based Search
• Scientific AI