Agentic system design is increasingly shifting from hand-crafted prompts and workflows toward automated search over agentic programs and interaction structures, with multi-agent systems receiving growing attention. Yet a central question remains unresolved: when does an automatically generated multi-agent structure exh...
Shao-Jun Xia, Yun-Er Zhang, Hui-Xin Zhang et al.· 0 citations
Vision-language models (VLMs) have emerged as powerful candidates for universal vision backbones, with representative architectures including autoregressive (AR) models and diffusion transformers (DiTs). Yet, adapting them efficiently for all-in-one low-level image restoration remains a challenge. Crucially, the field...
Shao-Jun Xia, Hui-Xin Zhang, Zhen Lei et al.· 0 citations
This paper frames memory hierarchy, cross-agent sharing, and consistency mechanisms around the need to reconcile interpretations and update dependent reasoning around the need to reconcile interpretations and update dependent reasoning inVision-language model agents.
Hui-Xin Zhang, Shao-Jun Xia, Di Wang et al.· 0 citations
T2T-VICL, a collaborative prompt-transfer framework, which converts mismatched visual demonstrations into implicit textual guidance without explicitly naming the tasks, is proposed.
