Open-Universe Assistance Games

Rachel Ma, Jingyi Qu, Andreea Bobu, Dylan Hadfield-Menell

Keywords: natural language processing, open-ended dialogue, open-universe, human-robot interaction

TL;DR: We formulated Open-Universe Assistance Games for reasoning over unbounded and evolving space of possible goals during multi-turn conversation with a user.

Abstract: Embodied AI agents must infer and act in an interpretable way on diverse human goals and preferences that are not predefined. To formalize this setting, we introduce Open-Universe Assistance Games (OU-AGs), a framework where the agent must reason over an unbounded and evolving space of possible goals. In this context, we introduce GOOD (GOals from Open-ended Dialogue), a data-efficient, online method that extracts goals in the form of natural language during an interaction with a human, and infers a distribution over natural language goals. GOOD prompts an LLM to simulate users with different complex intents, using its responses to perform probabilistic inference over candidate goals. This approach enables rich goal representations and uncertainty estimation without requiring large offline datasets. We evaluate GOOD in a text-based grocery shopping domain and in a text-operated simulated household robotics environment (AI2Thor), using synthetic user profiles. Our method outperforms a baseline without explicit goal tracking, as confirmed by both LLM-based and human evaluations.

Submission Number: 32