Go to ICLR 2026 Workshop MM Intelligence homepageCan Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
Track: long paper (up to 8 pages)
Keywords: Multi-modal, Large language Models, Vision and Language
TL;DR: Multimodal LLMs excel at conversation, yet their real-time, interactive, step-by-step coaching of everyday skills remains untested. We introduce LiveCook to assess this and reveal poor performance.
Abstract: Multi-modal Large Language Models (LLM) have advanced conversational abilities but struggle with providing live, interactive step-by-step guidance, a key capability for future AI assistants. Effective guidance requires not only delivering instructions but also detecting their successful execution, as well as identifying and alerting users to mistakes, all of which has to happen in real-time. This requires models that are not turn-based, but that can react asynchronously to a video stream, as well as video data showing users performing tasks including mistakes and their corrections. To this end, we introduce LiveCook, a new benchmark and dataset built upon CaptainCook4D, which contains user mistakes during task execution. Our dataset and benchmark features densely annotated, timed instructions and feedback messages, specifically including mistake alerts precisely timestamped to their visual occurrence in the video. We evaluate state-of-the-art multi-modal LLMs on the LiveCook benchmark and introduce LiveMamba, a streaming multi-modal LLM designed for interactive instructional guidance. This work provides the first dedicated benchmark and a strong baseline for developing and evaluating on live, situated coaching.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.
Submission Number: 16
Loading