EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation

TL;DR

EvoAgent is a novel framework that enhances large language models with skill learning, hierarchical delegation, and dynamic task decomposition, leading to significant improvements in real-world applications.

Contribution

It introduces a structured skill modeling approach, a multi-layer memory architecture, and a closed-loop skill optimization process for evolvable LLM agents.

Findings

GPT5.2 with EvoAgent improves professionalism, accuracy, and utility by ~28%.

The framework supports dynamic task decomposition and long-term capability growth.

Performance depends on synergy between model capabilities and agent architecture.

Abstract

This paper proposes EvoAgent - an evolvable large language model (LLM) agent framework that integrates structured skill learning with a hierarchical sub-agent delegation mechanism. EvoAgent models skills as multi-file structured capability units equipped with triggering mechanisms and evolutionary metadata, and enables continuous skill generation and optimization through a user-feedback-driven closed-loop process. In addition, by incorporating a three-stage skill matching strategy and a three-layer memory architecture, the framework supports dynamic task decomposition for complex problems and long-term capability accumulation. Experimental results based on real-world foreign trade scenarios demonstrate that, after integrating EvoAgent, GPT5.2 achieves significant improvements in professionalism, accuracy, and practical utility. Under a five-dimensional LLM-as-Judge evaluation protocol, the overall average score increases by approximately 28%. Further model transfer experiments indicate that the performance of an agent system depends not only on the intrinsic capabilities of the underlying model, but also on the degree of synergy between the model and the agent architecture.