From LLM-Driven Trading Card Generation to Procedural Relatedness: A Pokémon Case Study

• URL: http://arxiv.org/abs/2604.27972v1
• Date: Thu, 30 Apr 2026 15:03:25 GMT
• Title: From LLM-Driven Trading Card Generation to Procedural Relatedness: A Pokémon Case Study
• Abstract summary: This paper investigates the use of Large Language Models and Image Diffusion Models for Procedural Content Generation of TCG cards.<n>Modern generative AI not only enables large-scale content creation but could even introduce procedural relatedness.<n>We present a pipeline combining player-centric co-creation, fine-tuned embeddings, local LLMs, and Diffusion Models to generate dynamic, personalized cards.
• Score: 9.310318514564273
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Since the dawn of Trading Card Games, the genre has grown into a multi-billion-dollar industry engaging millions of analog and digital players worldwide. Popular TCGs rely on regular updates, balance adjustments, and rotating constraints to sustain engagement. Yet, as metagames stabilize, predictable strategies dominate and viable card options diminish, often resulting in repetitive and impaired player experiences. This paper investigates the use of Large Language Models and Image Diffusion Models for Procedural Content Generation of TCG cards, addressing these challenges by enabling a personalized infinity of card designs. Modern generative AI not only enables large-scale content creation but could even introduce procedural relatedness, fostering unique connections between players and their cards. We present a pipeline combining player-centric co-creation, fine-tuned embeddings, local LLMs, and Diffusion Models to generate dynamic, personalized cards while potentially expanding creative range. We evaluated the pipeline in a user study with 49 participants who generated 196 Pokémon card samples. Participants rated aesthetics and representativeness of visuals and mechanics, and provided qualitative feedback. Results show high satisfaction and indicate that most participants successfully realized their own ideas through prompt adjustments. These findings lay groundwork for future content generation systems and alternatives to conventional metagame evolution through procedural relatedness.

Related papers

• Predicting Drafted Deck Strength for "Magic: the Gathering" [16.700051324124143]
  Magic: the Gathering (MTG) exemplifies this setting, where the cards themselves define and alter gameplay rules, strategic constraints, and long-term outcomes.<n>We study Draft, a constrained deck-building format of MTG in which eight players make 39-45 sequential selections from semi-random packs to construct a 40-card deck under partial information.<n>We propose an encoder-based model that produces set-contextualized card embeddings to encode the draft decision sequence, with a consistent improvement over linear baselines on large-scale real-world data.
  arXiv  Detail & Related papers  (2026-07-06T08:12:35Z)
• Play Like Champions: Counterfactual Feedback Generation in Latent Space [10.090846922590462]
  We introduce Latent Maps of Performance, a framework for counterfactual path generation.<n>We trained a Guided Variational Autoencoder model on 23,305 professional tournament replays.<n>We conclude that there is a trade-off between the path-finding methods we employ and hope that future research will focus on developing model solutions for human improvement.
  arXiv  Detail & Related papers  (2026-06-30T21:15:34Z)
• PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game? [14.698359286590408]
  We present PTCG-Bench, a benchmark built on the Pok'emon Trading Card Game (PTCG)<n>Our experiments show that, although LLM agents can achieve non-trivial gameplay performance, sustained and stable self-evolution remains challenging.<n>We hope that PTCG-Bench will facilitate future research on harness-aware and self-evolving agents in realistic interactive environments.
  arXiv  Detail & Related papers  (2026-05-28T09:16:22Z)
• ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment [70.19758313256503]
  We propose ICG, a framework that integrates MLLM-based prompting with personalized preference alignment to generate contextually relevant covers.<n>ICG extracts semantic features from item titles and reference images via meta tokens, refines them with user embeddings, and injects the resulting personalized context into the diffusion model.<n>Experiments demonstrate that ICG significantly improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy.
  arXiv  Detail & Related papers  (2026-04-08T06:36:54Z)
• Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents [56.25101378553328]
  We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned keyboard-mouse inputs.<n>Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data.<n> Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks.
  arXiv  Detail & Related papers  (2025-10-27T17:43:51Z)
• Model as a Game: On Numerical and Spatial Consistency for Generative Games [117.36098212829766]
  We revisit the paradigm of generative games to explore what truly constitutes a Model as a Game (MaaG) with a well-developed mechanism.<n>Based on the DiT architecture, we design two specialized modules: (1) a numerical module that integrates a LogicNet to determine event triggers, with calculations processed externally as conditions for image generation; and (2) a spatial module that maintains a map of explored areas, retrieving location-specific information during generation and linking new observations to ensure continuity.
  arXiv  Detail & Related papers  (2025-03-27T05:46:15Z)
• Cardiverse: Harnessing LLMs for Novel Card Game Prototyping [9.029874576285085]
  Card games require extensive human effort in creative ideation and gameplay evaluation.<n>Recent advances in Large Language Models offer opportunities to automate these processes.<n>This paper introduces a comprehensive automated card game prototyping framework.
  arXiv  Detail & Related papers  (2025-02-10T23:47:35Z)
• Instruction-Driven Game Engines on Large Language Models [59.280666591243154]
  The IDGE project aims to democratize game development by enabling a large language model to follow free-form game rules. We train the IDGE in a curriculum manner that progressively increases the model's exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, a universally cherished card game.
  arXiv  Detail & Related papers  (2024-03-30T08:02:16Z)
• Zero-Shot Reasoning: Personalized Content Generation Without the Cold Start Problem [0.0]
  This paper presents a novel approach to achieving personalization by using large language models. We propose levels based on the gameplay data continuously collected from individual players. Our method has proven viable in a production setting and outperformed levels generated by traditional methods in the probability that a player will not quit the game mid-level.
  arXiv  Detail & Related papers  (2024-02-15T17:37:25Z)
• WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models [91.92346150646007]
  In this work, we introduce WinoGAViL: an online game to collect vision-and-language associations. We use the game to collect 3.5K instances, finding that they are intuitive for humans but challenging for state-of-the-art AI models. Our analysis as well as the feedback we collect from players indicate that the collected associations require diverse reasoning skills.
  arXiv  Detail & Related papers  (2022-07-25T23:57:44Z)
• Modeling Content Creator Incentives on Algorithm-Curated Platforms [76.53541575455978]
  We study how algorithmic choices affect the existence and character of (Nash) equilibria in exposure games. We propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.
  arXiv  Detail & Related papers  (2022-06-27T08:16:59Z)

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.