Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams

Researchers introduced Omni-InteractScope, a benchmark for evaluating how reliably omnimodal large language models (Omni-LLMs) connect evidence from continuous audiovisual streams to user needs and deliver timely, sustained interventions. The benchmark targets proactive and agentic interaction in continuous omnimodal streams, a setting the authors say existing evaluations cover only in limited depth.

Omnimodal large language models Omni-LLMs are increasingly expected to assist users while observing continuous audiovisual streams. However, existing evaluations provide limited insight into how reliably these models connect stream evidence and user needs to timely, sustained interventions. We int