AI RESEARCH
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
arXiv CS.AI
•
ArXi:2605.07177v1 Announce Type: cross Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective multimodal agents should search wider rather than longer: dispatching multiple grounded queries concurrently within a round.