让软件代理自主进化目标与代码，突破固定设计限制。
Self-Evolving Software Agents
- 用大模型与信念-意图-行动框架结合，实现自动演化
- 在动态环境中自主发现新目标并生成可执行代码
- 适合研究智能体自适应与自动化开发的学者
自主智能体虽能适应环境变化，但其需求、目标和能力在设计时即被固定，难以实现真正的软件演化。本文提出自演化软件代理，将信念-意图-行动（BDI）推理与大语言模型（LLM）结合，实现目标、推理逻辑和可执行代码的自主演化。我们设计了基于BDI-LLM的架构，其中自动化演化模块与智能体推理循环并行运行，通过经验提取新需求，并合成对应的设计与代码更新。一个原型在动态多智能体环境中测试显示，代理可在极少量先验知识下自主发现新目标并生成可执行行为。结果表明LLM驱动演化的可行性及其当前局限，尤其体现在行为继承与稳定性方面。
原文摘要 · Abstract (English)
Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software agents, combining BDI reasoning with LLMs to enable autonomous evolution of goals, reasoning, and executable code. We propose a BDI-LLM architecture in which an automated evolution module operates alongside the agent's reasoning loop, eliciting new requirements from experience and synthesizing corresponding design and code updates. A prototype evaluated in a dynamic multi-agent environment shows that agents can autonomously discover new goals and generate executable behaviours from minimal prior knowledge. The results indicate both the feasibility and current limits of LLM-driven evolution, particularly in terms of behavioural inheritance and stability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。