A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions
This addresses the need for more efficient and secure programming languages for LLM agents in AI applications, though it is incremental as it builds on existing agent frameworks.
The paper tackles the problem of using Python for LLM agents' code actions, which may lack performance, security, and reliability, by proposing Quasar, a new programming language that retains strong performance on tasks like visual question answering while reducing execution time by 42%, improving security by 52%, and enhancing reliability with conformal prediction.
Modern large language models (LLMs) are often deployed as agents, calling external tools adaptively to solve tasks. Rather than directly calling tools, it can be more effective for LLMs to write code to perform the tool calls, enabling them to automatically generate complex control flow such as conditionals and loops. Such code actions are typically provided as Python code, since LLMs are quite proficient at it; however, Python may not be the ideal language due to limited built-in support for performance, security, and reliability. We propose a novel programming language for code actions, called Quasar, which has several benefits: (1) automated parallelization to improve performance, (2) uncertainty quantification to improve reliability and mitigate hallucinations, and (3) security features enabling the user to validate actions. LLMs can write code in a subset of Python, which is automatically transpiled to Quasar. We evaluate our approach on the ViperGPT visual question answering agent, applied to the GQA dataset, demonstrating that LLMs with Quasar actions instead of Python actions retain strong performance, while reducing execution time when possible by 42%, improving security by reducing user approval interactions when possible by 52%, and improving reliability by applying conformal prediction to achieve a desired target coverage level.