Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Wenhan Wang, Zhixiang Zhou, Zhongtian Ma, Yanzhu Chen, Ziyu Lin, Hao Sheng, Pengfei Liu, Honglin Ma, Wenqi Shao, Qiaosheng Zhang, Yu Qiao

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.

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

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.

Paper Structure

This paper contains 26 sections, 1 equation, 4 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Dataset and Benchmark
  4. CiQi-VQA dataset
  5. CiQi-Bench
  6. Training Framework of CiQi-Agent
  7. Tool Design
  8. Two-phase Training Pipeline
  9. Reward Design
  10. LLM-as-a-Judge
  11. Experiments
  12. Experiment Setup
  13. Main Results on CiQi-Bench
  14. Ablation Study
  15. Conclusion
  16. ...and 11 more sections

Figures (4)

  • Figure 1: Comparison between (a) General-purpose MLLM and (b) CiQi-Agent. (a) Conventional MLLMs rely on single-pass answering, directly outputting a label leading to superficial or inaccurate identifications. (b) The proposed CiQi-Agent introduces Tool-Augmented Reasoning, enabling multi-step porcelain analysis through image zoom-in, image/text retrieval. This iterative process yields more reliable final answers aligned with expert connoisseurship reasoning.
  • Figure 2: Visualization of the four key attributes in porcelain connoisseurship. Shown are the distributions of dynasty, glaze color, vessel shape, and decorative motif in the raw porcelain dataset. For each attribute, the top 10 most frequent categories are presented.
  • Figure 3: Examples from CiQi-VQA dataset. The figure illustrates annotations across four key attributes: dynasty, glaze color, decorative motif and vessel shape.
  • Figure 4: Framework of the CiQi-Agent. The agent integrates visual zoom-in, image/text retrieval tools within a two-phase training pipeline. Supervised fine-tuning establishes tool-calling skills and porcelain connoisseurship knowledge, while reinforcement learning with an LLM-as-a-Judge refines accuracy and strategic tool-calling.