IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams 事件

IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams arXiv:2605.27074v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) achieve strong performance on reactive question answering, but real-world streaming assistants require proactive reasoning over continuous visual inputs. Existing benchmarks mainly study reactive or proactive interactions in isolated single-turn settings, overlooking dynamic multi-turn scenarios where users may