Many approaches to Natural Language Processing (NLP) tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, human language is inherently interactive, as evidenced by the back-and-forth nature of human conversations. In light of this, we posit that human-AI collaboration should also be interactive, with humans monitoring the work of AI agents and providing feedback that the agent can understand and utilize. Further, the AI agent should be able to detect when it needs additional information and proactively ask for help. Enabling this scenario would lead to more natural, efficient, and engaging human-AI collaborations. In this work, we explore these directions using the challenging task defined by the IGLU competition, an interactive grounded language understanding task in a MineCraft-like world. We explore multiple types of help players can give to the AI to guide it and analyze the impact of this help in AI behavior, resulting in performance improvements.

翻译：许多自然语言处理（NLP）任务的方法常将其视为单步问题：智能体接收指令、执行指令，并基于最终结果进行评估。然而，人类语言本质上是交互性的，人类对话中来回往复的特性便是明证。鉴于此，我们认为人机协作也应是交互式的，即人类监控AI智能体的工作，并提供智能体能够理解并利用的反馈。此外，AI智能体应能识别自身何时需要额外信息，并主动请求帮助。实现这一场景将促成更自然、更高效且更具吸引力的人机协作。在本研究中，我们以IGLU竞赛所定义的挑战性任务为背景探索这些方向——该竞赛是一个类似《我的世界》世界中的交互式基础语言理解任务。我们探索了玩家可以给予AI的多种帮助类型以引导其行为，并分析了这种帮助对AI行为的影响，最终实现了性能提升。