works on
benchmark 1multimodal large language model 1parallel action planning 1proactive agents 1task graphs 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.ROShow all

1 paper · 1 filter

cs.RO2026

ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response

Xiaomeng Zhu, Fengming Zhu, Weijie Zhou +8

The paper introduces ProAct-75, a benchmark of 75 proactive tasks with step‑level annotations and task graphs, and presents ProAct-Helper, a multimodal LLM that uses these graphs f…