From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop
This work addresses the challenge of enhancing LLMs' symbolic reasoning capabilities for AI researchers and developers, though it appears incremental as it builds on existing tool-calling and programming integration concepts.
The authors tackled the problem of integrating large language models with a persistent Lisp environment to enable dynamic tool creation and stateful memory, resulting in a novel architecture that supports reflective programming and interactive AI systems.
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.