Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems
2026-07-10 • Neural and Evolutionary Computing
Neural and Evolutionary ComputingArtificial IntelligenceComputational Engineering, Finance, and Science
AI summaryⓘ
The authors explain how artificial intelligence is moving from just solving specific tasks to creating systems that explore and learn over time using feedback. They discuss evolutionary computation (EC), a method that searches through many options but usually focuses on improving candidates for fixed problems. To help AI keep learning continuously, the authors propose evolutionary intelligence (EI), which combines improving candidates with remembering past experiences. They present a framework to understand how EI works and show its potential in different scientific tasks, while also pointing out challenges to overcome.
Artificial IntelligenceEvolutionary ComputationEvolutionary IntelligenceScientific DiscoveryCandidate RefinementExperience RetentionPopulation-Based SearchFeedback MechanismsAutomated Research Workflows
Authors
Chao Wang, Lingling Li, Fang Liu, Licheng Jiao
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.