From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop

2025/06/08 by de la Torre, Jordi · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Programming Languages (cs.PL)

paper · doi:10.48550/arxiv.2506.10021

Abstract

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.

Citations

• Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents
• Affective Coherence Monitoring for Transformer-Based Language Models
• Training language models to follow instructions with human feedback
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• Multitask Prompted Training Enables Zero-Shot Task Generalization
• Learning to summarize from human feedback
• Language Models are Few-Shot Learners
• Scaling Laws for Neural Language Models
• Deep reinforcement learning from human preferences
• Attention Is All You Need
• ImageNet classification with deep convolutional neural networks
• Recursive functions of symbolic expressions and their computation by machine, Part I
• The perceptron: A probabilistic model for information storage and organization in the brain.

Cited by

• The Biomimetic Architecture of Software 4.0

Related

• Towards Explainable and Language-Agnostic LLMs: Symbolic Reverse Engineering of Language at Scale
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
• Cognitive Modeling with Scaffolded LLMs: A Case Study of Referential Expression Generation
• LLMs as a synthesis between symbolic and distributed approaches to language
• Beyond LLMs: Advancing the Landscape of Complex Reasoning