Jiajun Wu

Large vision-language models (LVLMs) have made substantial advances in reasoning tasks at the Olympiad level. Nevertheless, current Olympiad-level multimodal reasoning benchmarks for these models often emphasize single-image analysis and fail to exploit contextual information across multiple imag...

Multi-agent systems powered by large language models have achieved strong performance on complex tasks, yet naive collaboration topologies often cause high communication costs and redundant context. Existing methods usually use a fixed communication graph and manage collaboration structure and sh...