Summary

AlgoEvo lets an agent inspect and edit executable candidates as tests return feedback. A skill hub separates design knowledge from the search engine, while a task tree records failed and successful paths. Across six benchmark tasks, the authors report matching or exceeding specialized search methods with fewer evaluations and tokens. The abstract does not supply exact deltas or a public implementation.

Why it matters
For algorithm-discovery workflows, preserving execution feedback as reusable task memory is worth testing. Wait for code and budget-matched reproduction before changing a production search pipeline.
Technical details
Design runtime feedback, design skill hub, hierarchical experience tree
Benchmarks six representative algorithm tasks
Reported Result matches or exceeds specialized methods with fewer evaluations and tokens
Code not linked on arXiv abstract page
Tags
agentic-searchalgorithm-discoveryskills