2 papers
cs.CV2026
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
Huanyao Zhang, Jiepeng Zhou, Jiaye Lin +9
Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence. However, training such agents remains constrained by limited c…
cs.CV2026
Long-MDR: Long-Context Reinforcement Learning for Multimodal Deep-Research Agents
On Tai Tang, Huanyao Zhang, Jiepeng Zhou +1
The next generation of multimodal research agents must reason over long-lived research histories rather than short model completions. During a single task, an agent may repeatedly…