SearchEyes unifies data, world and rewards to boost multimodal search agents
SearchEyes builds a simulated search world from a typed knowledge graph, tying together training data, environment, and step‑level rewards for multimodal agents. Its Perception‑Knowledge Chains and Hop‑Anchored Policy Optimization give agents fine‑grained credit, pushing open‑source multimodal search performance 6.2 points higher on average across six benchmarks.