Running 4 DISBench Leaderboard ๐ 4 Explore and submit multimodal image retrieval benchmark results
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning Paper โข 2603.03379 โข Published Mar 3 โข 32
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories Paper โข 2602.10809 โข Published Feb 11 โข 59
LawThinker: A Deep Research Legal Agent in Dynamic Environments Paper โข 2602.12056 โข Published Feb 12 โข 34