Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying
This addresses a key challenge in human-AI and robot-robot collaboration by isolating active uncertainty reduction as a prerequisite for safe interaction, though it is incremental in improving existing methods.
The paper tackled the problem of Privileged Information Bias in asymmetric embodied agents, where a knowledgeable Leader fails to guide a sensor-limited Follower due to lack of Theory of Mind, and found that active querying (Pull-based protocol) significantly improves robustness, with successful episodes featuring 2x the frequency of clarification requests.
Large Language Models (LLMs) act as powerful reasoning engines but struggle with "symbol grounding" in embodied environments, particularly when information is asymmetrically distributed. We investigate the Privileged Information Bias (or "Curse of Knowledge"), where a knowledgeable "Leader" agent fails to guide a sensor-limited "Follower" due to a lack of Theory of Mind. To quantify this phenomenon, we propose a novel Asymmetric Assistive Reasoning framework within AI2-THOR. Our experiments reveal a significant "Success Gap": while the Leader successfully perceives the target in 35.0% of episodes, the collaborative team succeeds only 17.0% of the time, implying that nearly 50% of feasible plans fail solely due to communicative grounding errors. We demonstrate that a "Pull-based" protocol (active querying) is significantly more robust than standard "Push-based" instruction, with successful episodes featuring 2x the frequency of clarification requests. This research isolates the mechanism of active uncertainty reduction as a prerequisite for safe human-AI and robot-robot collaboration.