Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments

TL;DR

This paper introduces middleware tools that significantly enhance large language models' ability to operate in complex environments by acting as an intermediary layer, demonstrated through improved performance in knowledge base and database tasks.

Contribution

The paper proposes a novel middleware tool class that augments LLMs, enabling better handling of environmental complexity in knowledge bases and databases.

Findings

GPT-4 with middleware achieves 2.8X better performance in database tasks.

GPT-4 with middleware achieves 2.2X better performance in KB tasks.

Middleware effectively shields LLMs from environmental complexity.

Abstract

The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist agents capable of operating within complex environments. These environments are often highly expansive, making it impossible for the LLM to process them within its short-term memory. Motivated by recent research on extending the capabilities of LLMs with tools, we seek to investigate the intriguing potential of tools to augment LLMs in handling such complexity by introducing a novel class of tools, termed middleware, to aid in the proactive exploration within these massive environments. Such specialized tools can serve as a middleware layer shielding the LLM from environmental complexity. In two representative complex environments -- knowledge bases (KBs) and databases -- we demonstrate the significant potential of augmenting language agents with tools in complex environments. Notably, equipped with the middleware, GPT-4 achieves 2.8X the performance of the best baseline in tasks requiring access to database content and 2.2X in KB tasks. Our findings illuminate the path for advancing language agents in real-world applications.