Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration

• URL: http://arxiv.org/abs/2603.29590v2
• Date: Wed, 01 Apr 2026 14:57:16 GMT
• Title: Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
• Abstract summary: We take inspiration from human authors' drawing practices and propose textbfFigAgent, a novel multi-agent framework for high-quality automatic MI generation.<n>Our FigAgent encapsulates drawing experiences from similar components across MIs and encapsulates them into reusable drawing illustrations.<n>A novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures.
• Score: 47.012967621189404
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration from human authors' drawing practices and correspondingly propose \textbf{FigAgent}, a novel multi-agent framework for high-quality automatic MI generation. Our FigAgent distills drawing experiences from similar components across MIs and encapsulates them into reusable drawing middlewares that can be orchestrated for MI generation, while evolving these middlewares to adapt to dynamically evolving drawing requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures. Extensive experiments show the efficacy of our method.

Related papers

• Text-to-Image Generative AI for Modeling and Simulation: Methods, Opportunities, and Applications [0.0]
  Text-to-image generation is a form of generative artificial intelligence (GenAI) that converts textual descriptions into images.<n>This tutorial introduces text-to-image generation to the modeling and simulation (M&S) community.
  arXiv  Detail & Related papers  (2026-06-18T23:48:32Z)
• Data-Efficient Brushstroke Generation with Diffusion Models for Oil Painting [60.15416769662556]
  We study the problem of learning human-like brushstroke generation from a small set of hand-drawn samples.<n>We propose StrokeDiff, a diffusion-based framework with Smooth Regularization (SmR)<n>We show how the learned primitives can be made controllable through a Bézier-based conditioning module.
  arXiv  Detail & Related papers  (2026-03-01T13:42:35Z)
• PaperBanana: Automating Academic Illustration for AI Scientists [58.120067704652314]
  PaperBanana is an agentic framework for automated generation of publication-ready academic illustrations.<n>Powered by state-of-the-art VLMs and image generation models, PaperBanana orchestrates specialized agents to retrieve references, plan content and style, render images, and iteratively refine via self-critique.
  arXiv  Detail & Related papers  (2026-01-30T18:33:37Z)
• Loomis Painter: Reconstructing the Painting Process [56.713812157283805]
  Step-by-step painting tutorials are vital for learning artistic techniques, but existing video resources lack interactivity and personalization.<n>We propose a unified framework for multi-media painting process generation with a semantics-driven style control mechanism.<n>We also build a large-scale dataset of real painting processes and evaluate cross-media consistency, temporal coherence, and final-image fidelity.
  arXiv  Detail & Related papers  (2025-11-21T16:06:32Z)
• The Landscape of Agentic Reinforcement Learning for LLMs: A Survey [103.32591749156416]
  The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL)<n>This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL.
  arXiv  Detail & Related papers  (2025-09-02T17:46:26Z)
• Large Language Model Agent: A Survey on Methodology, Applications and Challenges [88.3032929492409]
  Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence.<n>This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy.<n>Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time.
  arXiv  Detail & Related papers  (2025-03-27T12:50:17Z)
• PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning [4.173530949970536]
  This work introduces PCGRLLM, an extended architecture based on earlier work, which employs a feedback mechanism and several reasoning-based prompt engineering techniques.<n>We evaluate the proposed method on a story-to-reward generation task in a two-dimensional environment using two state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2025-02-15T21:00:40Z)
• Enhancing AI Research Paper Analysis: Methodology Component Extraction using Factored Transformer-based Sequence Modeling Approach [10.060305577353633]
  We propose a factored approach to sequence modeling, which leverages a broad-level category information of methodology domains. We conduct experiments following a simulated chronological setup (newer methodologies not seen during the training process) Our experiments demonstrate that the factored approach outperforms state-of-the-art baselines by margins of up to 9.257% for the methodology extraction task with the few-shot setup.
  arXiv  Detail & Related papers  (2023-11-05T16:33:35Z)
• Dynamically Grown Generative Adversarial Networks [111.43128389995341]
  We propose a method to dynamically grow a GAN during training, optimizing the network architecture and its parameters together with automation. The method embeds architecture search techniques as an interleaving step with gradient-based training to periodically seek the optimal architecture-growing strategy for the generator and discriminator.
  arXiv  Detail & Related papers  (2021-06-16T01:25:51Z)

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.