让大模型在持续运行的Lisp环境中自主创建和迭代工具
From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop
- 用中间件捕获大模型生成的Lisp代码并执行，实现动态交互
- 支持状态化外部记忆与程序自我反思，可长期演化工具链
- 适合研究符号计算与神经语言模型融合的开发者
我们提出一种将大语言模型（LLMs）与持久、交互式Lisp环境结合的新架构。该系统使大模型能够通过与实时REPL的程序化交互，自主定义、调用并演化自身工具。通过在生成内容中嵌入Lisp表达式，并利用中间件层拦截执行，系统实现了状态化外部记忆、反射式编程及动态工具创建。本文提出一个设计框架与架构原则，为未来集成符号编程与神经语言生成的交互式AI系统提供指导。
原文摘要 · Abstract (English)
We propose a novel architecture for integrating large language models (LLMs) with a persistent, interactive Lisp environment. This setup enables LLMs to define, invoke, and evolve their own tools through programmatic interaction with a live REPL. By embedding Lisp expressions within generation and intercepting them via a middleware layer, the system allows for stateful external memory, reflective programming, and dynamic tool creation. We present a design framework and architectural principles to guide future implementations of interactive AI systems that integrate symbolic programming with neural language generation.
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。