From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization

• URL: http://arxiv.org/abs/2505.16832v2
• Date: Tue, 27 May 2025 23:23:45 GMT
• Title: From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization
• Authors: Haonian Ji, Shi Qiu, Siyang Xin, Siwei Han, Zhaorun Chen, Dake Zhang, Hongyi Wang, Huaxiu Yao,
• Abstract summary: We introduce EduVisBench to better assess the visual reasoning capabilities of foundation models (FMs) in educational settings.<n>EduVisAgent coordinates specialized agents for instructional planning, reasoning decomposition, metacognitive prompting, and visualization design.<n>EduVisAgent substantially outperforms all baselines, achieving a 40.2% improvement and delivering more educationally aligned visualizations.
• Score: 21.902185151848517
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While foundation models (FMs), such as diffusion models and large vision-language models (LVLMs), have been widely applied in educational contexts, their ability to generate pedagogically effective visual explanations remains limited. Most existing approaches focus primarily on textual reasoning, overlooking the critical role of structured and interpretable visualizations in supporting conceptual understanding. To better assess the visual reasoning capabilities of FMs in educational settings, we introduce EduVisBench, a multi-domain, multi-level benchmark. EduVisBench features diverse STEM problem sets requiring visually grounded solutions, along with a fine-grained evaluation rubric informed by pedagogical theory. Our empirical analysis reveals that existing models frequently struggle with the inherent challenge of decomposing complex reasoning and translating it into visual representations aligned with human cognitive processes. To address these limitations, we propose EduVisAgent, a multi-agent collaborative framework that coordinates specialized agents for instructional planning, reasoning decomposition, metacognitive prompting, and visualization design. Experimental results show that EduVisAgent substantially outperforms all baselines, achieving a 40.2% improvement and delivering more educationally aligned visualizations. EduVisBench and EduVisAgent are available at https://github.com/aiming-lab/EduVisBench and https://github.com/aiming-lab/EduVisAgent.

Related papers

• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing [62.447497430479174]
  Drawing to reason in space is a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space.<n>Our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:41:50Z)
• From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models [65.0487600936788]
  Video Diffusion Models (VDMs) have emerged as powerful generative tools capable of synthesizing high-quality content.<n>We argue that VDMs naturally push to probe structured representations and an implicit understanding of the visual world.<n>Our method transforms each task into a visual transition, enabling the training of LoRA weights on short input- sequences.
  arXiv  Detail & Related papers  (2025-06-08T20:52:34Z)
• Explain with Visual Keypoints Like a Real Mentor! A Benchmark for Multimodal Solution Explanation [19.4261670152456]
  We introduce a novel task of visual solution explanation, which requires generating explanations that incorporate newly introduced visual elements essential for understanding.<n>We propose MathExplain, a benchmark consisting of 997 math problems annotated with visual keypoints and corresponding explanatory text that references those elements.<n>Our empirical results show that while some closed-source models demonstrate promising capabilities on visual solution-explaining, current open-source general-purpose models perform inconsistently.
  arXiv  Detail & Related papers  (2025-04-04T06:03:13Z)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
  We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories.<n>Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.<n>We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
  arXiv  Detail & Related papers  (2024-12-26T05:41:31Z)
• VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use [74.39058448757645]
  We present VipAct, an agent framework that enhances vision-language models (VLMs) VipAct consists of an orchestrator agent, which manages task requirement analysis, planning, and coordination, along with specialized agents that handle specific tasks. We evaluate VipAct on benchmarks featuring a diverse set of visual perception tasks, with experimental results demonstrating significant performance improvements.
  arXiv  Detail & Related papers  (2024-10-21T18:10:26Z)
• X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs [49.30255148577368]
  X-Former is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM. X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders. It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM.
  arXiv  Detail & Related papers  (2024-07-18T18:39:54Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• InsightSee: Advancing Multi-agent Vision-Language Models for Enhanced Visual Understanding [12.082379948480257]
  This paper proposes InsightSee, a multi-agent framework to enhance vision-language models' capabilities in handling complex visual understanding scenarios. The framework comprises a description agent, two reasoning agents, and a decision agent, which are integrated to refine the process of visual information interpretation. The proposed framework outperforms state-of-the-art algorithms in 6 out of 9 benchmark tests, with a substantial advancement in multimodal understanding.
  arXiv  Detail & Related papers  (2024-05-31T13:56:55Z)
• Veagle: Advancements in Multimodal Representation Learning [0.0]
  This paper introduces a novel approach to enhance the multimodal capabilities of existing models. Our proposed model Veagle, incorporates a unique mechanism inspired by the successes and insights of previous works. Our results indicate a improvement of 5-6 % in performance, with Veagle outperforming existing models by a notable margin.
  arXiv  Detail & Related papers  (2024-01-18T12:45:25Z)
• AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making [19.09644604789813]
  We develop Autonomous Visualization Agents (AVAs) that can interpret and accomplish user-defined visualization objectives through natural language. The addition of visual perception allows AVAs to act as the virtual visualization assistant for domain experts who may lack the knowledge or expertise in fine-tuning visualization outputs. Our study indicates that AVAs represent a general paradigm for designing intelligent visualization systems that can achieve high-level visualization goals.
  arXiv  Detail & Related papers  (2023-12-07T18:13:42Z)

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.