First Steps Towards Overhearing LLM Agents: A Case Study With Dungeons & Dragons Gameplay

TL;DR

This paper introduces the concept of overhearing LLM agents that listen to human conversations to assist, demonstrated through a Dungeons & Dragons case study using multimodal audio-language models, and evaluates their helpfulness.

Contribution

It pioneers the overhearing agents paradigm, exploring their potential in D&D gameplay and providing tools for future research in this area.

Findings

Some large audio-language models can perform overhearing tasks using audio cues

Overhearing agents can assist in gameplay without active participation

The study provides human evaluation data on agent helpfulness

Abstract

Much work has been done on conversational LLM agents which directly assist human users with tasks. We present an alternative paradigm for interacting with LLM agents, which we call "overhearing agents". These overhearing agents do not actively participate in conversation -- instead, they "listen in" on human-to-human conversations and perform background tasks or provide suggestions to assist the user. In this work, we explore the overhearing agents paradigm through the lens of Dungeons & Dragons gameplay. We present an in-depth study using large multimodal audio-language models as overhearing agents to assist a Dungeon Master. We perform a human evaluation to examine the helpfulness of such agents and find that some large audio-language models have the emergent ability to perform overhearing agent tasks using implicit audio cues. Finally, we release Python libraries and our project code to support further research into the overhearing agents paradigm at https://github.com/zhudotexe/overhearing_agents.