TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materials

Large Language Model (LLM) based AI educational content generation systems are increasingly being developed, yet no standardised benchmark exists to systematically evaluate them. This study introduces LessonBench-V1, a benchmark dataset comprising 647 human-written lessons paired with LLM-based reverse-engineered lesson plans across 240 STEM topics spanning mathematics, physics, chemistry, and computer science. The lessons are drawn from 97 trusted open sources, including LibreTexts, Brilliant.org and GeeksForGeeks. Each lesson plan is human-reviewed and produced through a pedagogically grounded methodology that synthesises Bloom's Taxonomy, Gagné's Events, Merrill's First Principles, and the 5E Instructional Model. The lesson plans capture 3,620 learning objectives with pedagogical metadata, enabling systematic, reproducible evaluation of lesson-generation AI agents and supporting further research. The study further proposes a three-dimensional evaluation pipeline for use with the dataset.

The need to evaluate instructional materials for K-12 science education has become increasingly important, as more educators use generative AI to create instructional materials. However, the review of instructional materials is time-consuming, expertise-intensive, and difficult to scale, motivating interest in automated evaluation approaches. While large language models (LLMs) have shown strong performance on general evaluation tasks, their performance and reliability on instructional materials remain unclear. To address this gap, we formulate Automatic Instructional Materials Evaluation (AIME) as a generative AI task that predicts scores and evidence using the rubric designed by the educator. We create a benchmark dataset and develop baseline models for AIME. First, we curate the first AIME dataset, SciEval, consisting of instructional materials annotated with pedagogy-aligned evaluation scores and evidence-based rationales. Expert annotations achieve high inter-rater reliability, resulting in a dataset of 273 lesson-level instructional materials evaluated across 13 criteria (N=3549) using the EQuIP rubric. Second, we test mainstream LLMs (GPT, Gemini, Llama, and Qwen) on SciEval and find that none achieve strong performance. Then we fine-tune Qwen3 on SciEval. Results on a held-out test set show that domain-aligned fine-tuning can achieve up to 11 percent performance gains, highlighting the importance of domain-specific fine-tuning for AIME and facilitating the use of LLMs in other educational tasks.

As agents rapidly evolve, existing benchmarks can become saturated, limiting their ability to distinguish capabilities and reveal remaining failure modes. Particularly in scientific domains, constructing and updating benchmarks requires substantial time, labor, and domain expertise, making it difficult to keep evaluation aligned with advances in agent capabilities. We address this challenge by investigating whether scientific-agent benchmarks can be automatically generated and iteratively adapted as agent capabilities evolve. We introduce AutoSciBench, a framework that represents each task as a high-level concept specifying the scientific domain, data modality, and required reasoning approach, together with a low-level recipe specifying how the question, environment, and ground-truth answer are constructed and verified. Agents attempt to solve each task, producing solver trajectories and corresponding judge feedback which AutoSciBench uses to revise the recipe or concept, closing observed shortcuts and shifting tasks toward raw-data re-examination, interpretation of intermediate results, and evidence integration. Experience distilled from completed refinement trajectories further guides new concept generation, allowing lessons from earlier task refinement to inform subsequent benchmark construction. Starting from existing benchmarks, we evaluate AutoSciBench across computational biology, materials science, and clinical imaging. Generated benchmarks reduce average solver accuracy by 22.4 and 25.5 percentage points relative to the human-curated benchmarks in computational biology and materials science, respectively, while generated tasks receive higher average quality ratings across all three domains, suggesting that scientific-agent evaluation can adapt as agent capabilities advance.