一作ACL 2026Findings· Findings of ACL
L ang2 A ct: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains
Yuqi Xiong · Chunyi Peng · Zhipeng Xu · Zhenghao Liu · Zulong Chen · Yukun Yan · Shuo Wang · Yu Gu · Ge Yu
摘要
Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend the perceptual capabilities of VLMs, typically by explici...