自演化软件代理
Self-Evolving Software Agents
- University of Trento（特伦托大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出自演化软件代理，结合BDI推理与大语言模型，使代理能自主进化目标、推理和可执行代码。实验显示代理可自主发现新目标并生成行为，验证了LLM驱动进化的可行性与局限性。
AI中文摘要：
自主代理可以适应变化的环境，但受限于设计时固定的请求、目标和能力，阻碍了真正的软件进化。本文引入自演化软件代理，结合BDI推理与大语言模型，使代理能够自主进化目标、推理和可执行代码。我们提出了一种BDI-LLM架构，其中自动进化模块与代理的推理循环并行运行，从经验中提取新需求，并合成相应的设计和代码更新。在动态多代理环境中评估的原型显示，代理能够从最小的先前知识中自主发现新目标并生成可执行行为。结果表明了LLM驱动进化的可行性和当前限制，特别是在行为继承和稳定性方面。
英文摘要：
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.
