A Creative Agent is Worth a 64-Token Template

• URL: http://arxiv.org/abs/2603.17895v1
• Date: Wed, 18 Mar 2026 16:25:52 GMT
• Title: A Creative Agent is Worth a 64-Token Template
• Abstract 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.<n>We introduce textbfCAT, a framework for textbfAgent textbfTokenization that encapsulates agents' intrinsic understanding of creativity'' through a textitCreative Tokenizer.
• Score: 31.988429473627594
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model [4.685207648946472]
  STEDiff is a training-free method designed to enhance semantic representations directly within the text-embedding space.<n>Our method notably improves semantic consistency and generation in complex scenarios.
  arXiv  Detail & Related papers  (2026-06-09T09:59:09Z)
• Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting [24.62226758388138]
  Current text-to-image (T2I) models are largely optimized for literal text-image alignment with their data distribution.<n>We propose a Self-Creative Diffusion (SCDiff) model for meaningful T2I generations featuring two core modules.<n>Our model substantially improves creativity, semantic alignment, and visual coherence, offering a simple yet powerful framework for generating creative objects.
  arXiv  Detail & Related papers  (2026-05-19T08:52:18Z)
• Show, Don't Tell: Morphing Latent Reasoning into Image Generation [60.743575139661154]
  Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation.<n>We introduce LatentMorph, a framework that seamlessly integrates implicit latent reasoning into the T2I generation process.<n>By performing reasoning entirely in continuous latent spaces, LatentMorph avoids the bottlenecks of explicit reasoning and enables more adaptive self-refinement.
  arXiv  Detail & Related papers  (2026-02-02T15:29:48Z)
• VLM-Guided Adaptive Negative Prompting for Creative Generation [21.534474554320823]
  Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance.<n>We propose VLM-Guided Adaptive Negative-Prompting, a training-free, inference-time method that promotes creative image generation.<n>We show consistent gains in creative novelty with negligible computational overhead.
  arXiv  Detail & Related papers  (2025-10-12T17:34:59Z)
• AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models [58.85362281293525]
  We introduce AcT2I, a benchmark designed to evaluate the performance of T2I models in generating images from action-centric prompts.<n>We experimentally validate that leading T2I models do not fare well on AcT2I.<n>We build upon this by developing a training-free, knowledge distillation technique utilizing Large Language Models to address this limitation.
  arXiv  Detail & Related papers  (2025-09-19T16:41:39Z)
• RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning [88.14234949860105]
  RePrompt is a novel reprompting framework that introduces explicit reasoning into the prompt enhancement process via reinforcement learning.<n>Our approach enables end-to-end training without human-annotated data.
  arXiv  Detail & Related papers  (2025-05-23T06:44:26Z)
• Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation [39.93527514513576]
  Creative'' remains an inherently abstract concept for both humans and diffusion models.<n>Current methods rely heavily on reference prompts or images to achieve a creative effect.<n>We introduce CreTok, which brings meta-creativity to diffusion models by redefining creative' as a new token, texttCreTok>.<n>Code will be made available at https://github.com/fu-feng/CreTok.
  arXiv  Detail & Related papers  (2024-10-31T17:19:03Z)
• Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation [149.96612254604986]
  PRISM is an algorithm that automatically produces human-interpretable and transferable prompts.<n>Inspired by large language model (LLM) jailbreaking, PRISM leverages the in-context learning ability of LLMs to iteratively refine the candidate prompt distribution.<n>Our experiments demonstrate the versatility and effectiveness of PRISM in generating accurate prompts for objects, styles, and images across multiple T2I models.
  arXiv  Detail & Related papers  (2024-03-28T02:35:53Z)
• Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models [103.61066310897928]
  Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt. While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt. We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect, where the model fails to generate one or more of the subjects from the input prompt. We introduce the concept of Generative Semantic Nursing (GSN), where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness
  arXiv  Detail & Related papers  (2023-01-31T18:10:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.