让AI主动发现能帮人减轻负担的未来任务，提升机器人应变能力。
Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search
- 构建多智能体搜索树框架，分步分解复杂任务推理。
- 在2000+真实场景视频上表现超越现有模型，显著降低人类工作量。
- 适合研究人机协作、开放未来任务规划的开发者与研究员。
近期机器人与具身AI的发展主要由大型多模态模型（LMMs）推动，但一个关键挑战仍被忽视：如何让LMMs在人类意图高度并发且动态的开放未来场景中，主动发现有助于人类的任务。本文正式提出以人为中心的开放未来任务发现（HOTD）问题，聚焦于识别可减少人类在未来多种可能情景下负担的任务。为此，我们构建了HOTD-Bench基准，包含超过2000个真实世界视频、半自动化标注流程及面向开放集未来的仿真评估协议。此外，提出协同多智能体搜索树（CMAST）框架，通过多智能体系统分解复杂推理，并以可扩展的搜索树结构组织推理过程。实验表明，CMAST在HOTD-Bench上表现最佳，显著优于现有LMMs，且能有效集成到已有模型中，持续提升性能。
原文摘要 · Abstract (English)
Recent progress in robotics and embodied AI is largely driven by Large Multimodal Models (LMMs). However, a key challenge remains underexplored: how can we advance LMMs to discover tasks that assist humans in open-future scenarios, where human intentions are highly concurrent and dynamic. In this work, we formalize the problem of Human-centric Open-future Task Discovery (HOTD), focusing particularly on identifying tasks that reduce human effort across plausible futures. To facilitate this study, we propose HOTD-Bench, which features over 2K real-world videos, a semi-automated annotation pipeline, and a simulation-based protocol tailored for open-set future evaluation. Additionally, we propose the Collaborative Multi-Agent Search Tree (CMAST) framework, which decomposes complex reasoning through a multi-agent system and structures the reasoning process through a scalable search tree module. In our experiments, CMAST achieves the best performance on the HOTD-Bench, significantly surpassing existing LMMs. It also integrates well with existing LMMs, consistently improving performance.
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。