2026
MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents
ICLR 2026poster
Existing multimodal browsing benchmarks often fail to require genuine multimodal reasoning, as many tasks can be solved with text-only heuristics without vision-in-the-loop verification. We introduce MMSearch-Plus, a 311-task benchmark that enforces multimodal understanding by requiring extraction a…