CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains

TL;DR

CiQi-Agent is a multimodal AI system designed for detailed analysis and connoisseurship of Chinese porcelain, integrating vision, retrieval, and reasoning to outperform existing models on a large expert-annotated dataset.

Contribution

The paper introduces CiQi-Agent, a novel multimodal agent with a large dataset and benchmark for Chinese porcelain analysis, enabling fine-grained, explainable connoisseurship.

Findings

CiQi-Agent outperforms all competitive models on six porcelain attributes.

Achieves 12.2% higher accuracy than GPT-5 on CiQi-Bench.

The dataset and model are publicly available for research.

Abstract

The connoisseurship of antique Chinese porcelain demands extensive historical expertise, material understanding, and aesthetic sensitivity, making it difficult for non-specialists to engage. To democratize cultural-heritage understanding and assist expert connoisseurship, we introduce CiQi-Agent -- a domain-specific Porcelain Connoisseurship Agent for intelligent analysis of antique Chinese porcelain. CiQi-Agent supports multi-image porcelain inputs and enables vision tool invocation and multimodal retrieval-augmented generation, performing fine-grained connoisseurship analysis across six attributes: dynasty, reign period, kiln site, glaze color, decorative motif, and vessel shape. Beyond attribute classification, it captures subtle visual details, retrieves relevant domain knowledge, and integrates visual and textual evidence to produce coherent, explainable connoisseurship descriptions. To achieve this capability, we construct a large-scale, expert-annotated dataset CiQi-VQA, comprising 29,596 porcelain specimens, 51,553 images, and 557,940 visual question--answering pairs, and further establish a comprehensive benchmark CiQi-Bench aligned with the previously mentioned six attributes. CiQi-Agent is trained through supervised fine-tuning, reinforcement learning, and a tool-augmented reasoning framework that integrates two categories of tools: a vision tool and multimodal retrieval tools. Experimental results show that CiQi-Agent (7B) outperforms all competitive open- and closed-source models across all six attributes on CiQi-Bench, achieving on average 12.2\% higher accuracy than GPT-5. The model and dataset have been released and are publicly available at https://huggingface.co/datasets/SII-Monument-Valley/CiQi-VQA.