Tag
This paper introduces On-Policy Data Evolution (ODE) and a visual-native agent harness to improve multimodal deep search agents. By enabling reusable visual evidence and closed-loop data generation, ODE significantly boosts the performance of Qwen3-VL agents across multiple benchmarks, surpassing Gemini 2.5 Pro.
HyperEyes is a parallel multimodal search agent that uses dual-grained reinforcement learning to optimize inference efficiency, achieving higher accuracy with significantly fewer tool-call rounds compared to existing agents.
InterLV-Search is a new benchmark introduced in this paper to evaluate interleaved language-vision agentic search, highlighting limitations in current systems regarding visual evidence seeking and multimodal integration.