SOURCE-LINKED INTELLIGENCE

AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-defined control flows. This limitation restricts adaptive reasoning, blocks cross-paradigm transfer, and discards valuable execution feedback. We propose AlgoEvo, a unified agentic framework that transforms automated algorithm discovery into an interactive, knowledge-accumulating process. An autonomous agent dynamically inspects, diagnoses, and edits code based on runtime feedback. A design skill hub decouples paradigm-specific

Read original source ↗ Open in workspace

recordType

paper

region

Global