First Steps Towards Overhearing LLM Agents: A Case Study With Dungeons & Dragons Gameplay
This introduces a novel interaction paradigm for LLM agents that could benefit users in collaborative settings like gaming, though it is incremental as it builds on existing conversational agent work.
The paper tackles the problem of assisting users through LLM agents that passively listen to human conversations, exploring this 'overhearing agents' paradigm in Dungeons & Dragons gameplay and finding that some large audio-language models can perform these tasks using implicit audio cues.
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.