MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents

TL;DR

MOSS is a framework that enables AI agents to evolve and adapt through code by managing runtime context and ensuring consistency across interactions, advancing towards Turing-complete, autonomous agents.

Contribution

This paper introduces MOSS, a novel framework integrating code generation with dynamic context management to improve AI agent adaptability and consistency.

Findings

Enhances agent efficiency and capability through context-aware code execution.

Facilitates seamless tool integration and runtime instance replacement.

Supports development of Turing-complete, evolving AI agents.

Abstract

Developing AI agents powered by large language models (LLMs) faces significant challenges in achieving true Turing completeness and adaptive, code-driven evolution. Current approaches often generate code independently of its runtime context, relying heavily on the LLM's memory, which results in inefficiencies and limits adaptability. Manual protocol development in sandbox environments further constrains the agent's autonomous adaptability. Crucially, achieving consistency in code and context across multi-turn interactions and ensuring isolation of local variables within each interaction remains an unsolved problem. We introduce MOSS (llM-oriented Operating System Simulation), a novel framework that addresses these challenges by integrating code generation with a dynamic context management system. MOSS ensures consistency and adaptability by using a mechanism that maintains the Python context across interactions, including isolation of local variables and preservation of runtime integrity. At its core, the framework employs an Inversion of Control (IoC) container in conjunction with decorators to enforce the least knowledge principle, allowing agents to focus on abstract interfaces rather than concrete implementations. This facilitates seamless integration of new tools and libraries, enables runtime instance replacement, and reduces prompt complexity, providing a "what you see is what you get" environment for the agent. Through a series of case studies, we show how this framework can enhance the efficiency and capabilities of agent development and highlight its advantages in moving towards Turing-complete agents capable of evolving through code.