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

2026-04-21

AI Summary

This work addresses the challenges of continual learning and efficient collaboration among large language model (LLM) agents in complex tasks by proposing an evolvable agent framework. The framework integrates structured skill units, a hierarchical multi-agent delegation mechanism, a three-stage skill-matching strategy, and a three-layer memory architecture, all orchestrated within a user feedback–driven closed-loop system that enables co-evolution of skills and architecture. When instantiated with GPT-5.2 in an international trade scenario, the system demonstrates substantial improvements in domain expertise, accuracy, and practical utility, achieving a 28% average gain across five dimensions in LLM-as-Judge evaluations, thereby validating the efficacy and novelty of the proposed approach.

Technology Category

Multiagent Systems: Multiagent LearningCognitive Modeling & Cognitive Systems: Agent ArchitecturesMachine Learning: Large Multimodal Models (LMMs)

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsSearch and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved informationEconomics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

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.

Problem

• evolvable agent
• skill learning
• multi-agent delegation
• task decomposition
• LLM agent framework

Innovation

• Evolvable Agent
• Structured Skill Learning
• Multi-Agent Delegation
• Closed-Loop Skill Evolution
• Hierarchical Task Decomposition