主动提问可解决智能体间信息不对称导致的协作失效问题
Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying
- 用主动提问代替被动指令，提升信息传递效率
- 协作成功率从35.0%降至17.0%，因沟通误差损失近一半可行方案
- 适合研究人机协作、机器人团队通信与主动感知的读者
大型语言模型在具身环境中面临符号接地难题，尤其当信息分布不对称时。本文研究了‘知识诅咒’现象——知情的‘领导者’智能体无法有效指导感知受限的‘跟随者’，原因在于缺乏心智理论。我们在AI2-THOR框架中提出一种新型非对称辅助推理机制，实验显示：尽管领导者在35.0%的回合中能成功识别目标，但协作团队整体成功率仅为17.0%，表明近50%的可行计划因沟通接地失败而中断。研究发现，‘拉取式’协议（主动提问）比标准‘推送式’指令更稳健，成功案例中澄清请求频率高出2倍。该工作揭示主动不确定性降低是实现安全人机与机器人协作的关键前提。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。