Reliable Collaborative Conversational Agent System Based on LLMs and Answer Set Programming

TL;DR

This paper introduces a dual-agent system combining Large Language Models and Answer Set Programming to enhance reliability and security in task-oriented dialogue systems, demonstrated through a fast-food drive-through application.

Contribution

It presents a novel collaborative paradigm using ASP-driven agents sharing a knowledge base for reliable, secure, and consistent task execution in conversational AI.

Findings

AutoManager outperforms real-world Taco Bell AI in reliability.

Knowledge sharing via ASP ensures consistency and security.

Dual-agent system improves task accuracy and robustness.

Abstract

As the Large-Language-Model-driven (LLM-driven) Artificial Intelligence (AI) bots became popular, people realized their strong potential in Task-Oriented Dialogue (TOD). However, bots relying wholly on LLMs are unreliable in their knowledge, and whether they can finally produce a correct outcome for the task is not guaranteed. The collaboration among these agents also remains a challenge, since the necessary information to convey is unclear, and the information transfer is by prompts: unreliable, and malicious knowledge is easy to inject. With the help of knowledge representation and reasoning tools such as Answer Set Programming (ASP), conversational agents can be built safely and reliably, and communication among the agents made more reliable as well. We propose a Manager-Customer-Service Dual-Agent paradigm, where ASP-driven bots share the same knowledge base and complete their assigned tasks independently. The agents communicate with each other through the knowledge base, ensuring consistency. The knowledge and information conveyed are encapsulated and invisible to the users, ensuring the security of information transmission. To illustrate the dual-agent conversational paradigm, we have constructed AutoManager, a collaboration system for managing the drive-through window of a fast-food restaurant such as Taco Bell in the US. In AutoManager, the customer service bot takes the customer's order while the manager bot manages the menu and food supply. We evaluated our AutoManager system and compared it with the real-world Taco Bell Drive-Thru AI Order Taker, and the results show that our method is more reliable.