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.
@article{arxiv.2511.18929,
title = {Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search},
author = {Zijian Song and Xiaoxin Lin and Tao Pu and Zhenlong Yuan and Guangrun Wang and Liang Lin},
journal= {arXiv preprint arXiv:2511.18929},
year = {2025}
}