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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Aimin, Guo, Jiajing, Jia, Fuwei, Lv, Chen, Wang, Boyu, Li, Fangzheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918465784250368
author Zhang, Aimin
Guo, Jiajing
Jia, Fuwei
Lv, Chen
Wang, Boyu
Li, Fangzheng
author_facet Zhang, Aimin
Guo, Jiajing
Jia, Fuwei
Lv, Chen
Wang, Boyu
Li, Fangzheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20133
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
Zhang, Aimin
Guo, Jiajing
Jia, Fuwei
Lv, Chen
Wang, Boyu
Li, Fangzheng
Artificial Intelligence
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.
title EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
topic Artificial Intelligence
url https://arxiv.org/abs/2604.20133