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

2026-04-22 · Aimin Zhang, Jiajing Guo, Fuwei Jia, Chen Lv, Boyu Wang, Fangzheng Li arxiv

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. Code, data, and documents will be released at https://github.com/Focus-AI-Center/Mentarc-EvoAgent.git.

📄 PDF Abstract BibTeX arXiv:2604.20133

Code (0)

등록된 구현이 없습니다.

RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution

2026-08-27 · Junjie Zhang, Hui Liu, Kecheng Chen, Xianbo Mo 외 arxiv

LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks than unsafe text generation alone. Exist…

Text Generation

EvoAgentX: An Automated Framework for Evolving Agentic Workflows

2025-07-04 · Yingxu Wang, Siwei Liu, Jinyuan Fang, Zaiqiao Meng

Multi-agent systems (MAS) have emerged as a powerful paradigm for orchestrating large language models (LLMs) and specialized tools to collaboratively address complex tasks. However, existing MAS frameworks often require …

Code Generation Math Mathematical Problem-Solving mbpp

EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

2024-06-20 · Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan 외

The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that…

Evolutionary Algorithms

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

2026-07-06 · Xingze Gao, Chuanrui Hu, Hongda Chen, Pengfei Yao 외 arxiv

Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and verification. Yet current evaluations do n…

Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents

2026-05-20 · Zijian Du, Nathaniel Pinckney arxiv

Complex Verilog Design Problems (CVDP) challenge hardware LLM agents because solving them requires localizing verifier-relevant RTL, testbenches, include paths, and build dependencies inside large repository snapshots, m…