Paper
A Creative Agent is Worth a 64-Token Template
Authors
Ruixiao Shi, Fu Feng, Yucheng Xie, Xu Yang, Jing Wang, Xin Geng
Abstract
Text-to-image (T2I) models have substantially improved image fidelity and prompt adherence, yet their creativity remains constrained by reliance on discrete natural language prompts. When presented with fuzzy prompts such as ``a creative vinyl record-inspired skyscraper'', these models often fail to infer the underlying creative intent, leaving creative ideation and prompt design largely to human users. Recent reasoning- or agent-driven approaches iteratively augment prompts but incur high computational and monetary costs, as their instance-specific generation makes ``creativity'' costly and non-reusable, requiring repeated queries or reasoning for subsequent generations. To address this, we introduce \textbf{CAT}, a framework for \textbf{C}reative \textbf{A}gent \textbf{T}okenization that encapsulates agents' intrinsic understanding of ``creativity'' through a \textit{Creative Tokenizer}. Given the embeddings of fuzzy prompts, the tokenizer generates a reusable token template that can be directly concatenated with them to inject creative semantics into T2I models without repeated reasoning or prompt augmentation. To enable this, the tokenizer is trained via creative semantic disentanglement, leveraging relations among partially overlapping concept pairs to capture the agent's latent creative representations. Extensive experiments on \textbf{\textit{Architecture Design}}, \textbf{\textit{Furniture Design}}, and \textbf{\textit{Nature Mixture}} tasks demonstrate that CAT provides a scalable and effective paradigm for enhancing creativity in T2I generation, achieving a $3.7\times$ speedup and a $4.8\times$ reduction in computational cost, while producing images with superior human preference and text-image alignment compared to state-of-the-art T2I models and creative generation methods.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.17895v1</id>\n <title>A Creative Agent is Worth a 64-Token Template</title>\n <updated>2026-03-18T16:25:52Z</updated>\n <link href='https://arxiv.org/abs/2603.17895v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.17895v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Text-to-image (T2I) models have substantially improved image fidelity and prompt adherence, yet their creativity remains constrained by reliance on discrete natural language prompts. When presented with fuzzy prompts such as ``a creative vinyl record-inspired skyscraper'', these models often fail to infer the underlying creative intent, leaving creative ideation and prompt design largely to human users. Recent reasoning- or agent-driven approaches iteratively augment prompts but incur high computational and monetary costs, as their instance-specific generation makes ``creativity'' costly and non-reusable, requiring repeated queries or reasoning for subsequent generations. To address this, we introduce \\textbf{CAT}, a framework for \\textbf{C}reative \\textbf{A}gent \\textbf{T}okenization that encapsulates agents' intrinsic understanding of ``creativity'' through a \\textit{Creative Tokenizer}. Given the embeddings of fuzzy prompts, the tokenizer generates a reusable token template that can be directly concatenated with them to inject creative semantics into T2I models without repeated reasoning or prompt augmentation. To enable this, the tokenizer is trained via creative semantic disentanglement, leveraging relations among partially overlapping concept pairs to capture the agent's latent creative representations. Extensive experiments on \\textbf{\\textit{Architecture Design}}, \\textbf{\\textit{Furniture Design}}, and \\textbf{\\textit{Nature Mixture}} tasks demonstrate that CAT provides a scalable and effective paradigm for enhancing creativity in T2I generation, achieving a $3.7\\times$ speedup and a $4.8\\times$ reduction in computational cost, while producing images with superior human preference and text-image alignment compared to state-of-the-art T2I models and creative generation methods.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-18T16:25:52Z</published>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Ruixiao Shi</name>\n </author>\n <author>\n <name>Fu Feng</name>\n </author>\n <author>\n <name>Yucheng Xie</name>\n </author>\n <author>\n <name>Xu Yang</name>\n </author>\n <author>\n <name>Jing Wang</name>\n </author>\n <author>\n <name>Xin Geng</name>\n </author>\n </entry>"
}