FreeEvolve: Learning to Evolve Beyond Fixed Loops

2026-10-06

AI Summary

Existing agent evolvers rely on manually designed, fixed search loops and lack autonomous decision-making capabilities. This work proposes a meta-evolution framework that reformulates the optimization process itself as a learnable skill, enabling the evolver to autonomously determine testing, evaluation, and termination strategies. Specifically, the proposed method iteratively refines editable evolution skills by scoring newly generated agents, thereby achieving fully automated and adaptive pipelines. Experimental results demonstrate that this framework yields an average improvement of 13.6 points on primary metrics across multiple benchmarks, significantly outperforming handcrafted approaches. Furthermore, the acquired evolution skills exhibit strong transferability across diverse environments.

Abstract

Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is still designed by hand: a fixed search loop decides how candidates are evaluated, which are kept and when the search stops. We propose FREEEVOLVE, which automates this process as well. An environment specifies the goal, target agent, evaluator, data and resource limits; within these limits, the evolver itself decides what to test, how much evidence to collect, which candidates to pursue and when to stop. These decisions follow an editable evolution skill, which we improve through meta-evolution by scoring each candidate skill on the fresh target agent it produces. The optimization process thus becomes a capability learned from experience rather than a loop engineered in advance. On tau3-bench, ARC-AGI-2, ARC-AGI-3 and Terminal-Bench 2.1, FREEEVOLVE controls the evolution campaign by itself, yet improves the primary held-out metric by 13.6 points on average and matches or exceeds hand-designed evolvers. The learned process keeps improving with experience: meta-evolved skills add 6.9 points over the seed skill on fresh target agents, demonstrating transferability across environments.

Problem

• Agent Evolution
• Automated Prompt Engineering
• Search Loop Optimization
• Meta-evolution

Innovation

• Agent Evolver
• Meta-Evolution
• Automated Optimization
• Evolution Skill
• LLM Agents