# AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery

arXiv: https://arxiv.org/abs/2609.15820 · HTML: https://mlsanity.com/paper/2609.15820/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 47 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 11 of 11)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [LLM4AD: A Platform for Algorithm Design with Large Language Model](https://mlsanity.com/paper/2412.17287/) (2024)
- [From Context to Skills: Can Language Models Learn from Context Skillfully?](https://mlsanity.com/paper/2604.27660/) (2026)
- [SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering](https://mlsanity.com/paper/2604.09297/) (2026)
- [More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries](https://mlsanity.com/paper/2605.24050/) (2026)
- [MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework](https://mlsanity.com/paper/2508.03929/) (2025)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents](https://mlsanity.com/paper/2607.22520/) (2026)
- [EvoDR: Evolving Dispatching Rules via Large Language Model for Dynamic Flexible Assembly Flow Shop Scheduling](https://mlsanity.com/paper/2601.15738/) (2026)

## Built on by (most cited first, 2 of 2)

- [AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding](https://mlsanity.com/paper/2610.05334/) (2026)
- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)

## Abstract (arXiv)

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 overlooks richer execution feedback. To bridge this gap, we introduce an end-to-end framework, AlgoEvo, a unified agentic architecture 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 knowledge from the core discovery engine, allowing a unified workflow to seamlessly handle single-heuristic, multi-objective, and multi-component design. Meanwhile, a hierarchical experience bank organizes search trajectories into a task-level tree to guide exploration and consolidates cross-task patterns into reusable skills. Across six representative benchmark tasks, AlgoEvo reaches state-of-the-art performance with as little as 7% of the evaluation budget and reduced token consumption, demonstrating strong intra-task accumulation, cross-task transfer, and the ability to reproduce or exceed the strongest existing methods through flexible skill activation.