Hongran An

Hongran An, Zonglin Yang

Large language models (LLMs) show remarkable potential in scientific hypothesis discovery. However, existing approaches face two critical limitations: they treat divergent exploratory ideation and convergent fine-grained refinement as isolated tasks, and they operate autonomously with little to no human guidance. We present MOOSE-Copilot, the first unified framework to bridge this abstraction gap through a formalized human-AI interaction (HAII) protocol. Our system empowers scientists to steer the generative process via three explicit signals: initial blueprints, inter-stage routing, and regenerative feedback. Quantitative evaluations demonstrate that injecting these structured expert signals significantly outperforms purely autonomous baselines, establishing a performance ceiling under oracle guidance. Furthermore, to democratize this paradigm, we develop an intuitive web-based interface featuring interactive tree visualization. This explicitly eliminates the steep learning curve of complex command-line agentic tools, empowering interdisciplinary researchers to directly leverage, visually orchestrate, and accelerate end-to-end scientific breakthroughs.

Congren Dai, Yue Yang, Krinos Li et al.

Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of Large Language Models and Vision-Language Models to interpret full musical notation remains insufficiently examined. We introduce the Musical Score Understanding Benchmark (MSU-Bench), the first large-scale, human-curated benchmark for score-level musical understanding across textual (ABC notation) and visual (PDF) modalities. MSU-Bench contains 1,800 generative Question-Answering pairs from works by Bach, Beethoven, Chopin, Debussy, and others, organised into four levels of increasing difficulty, ranging from onset information to texture and form. Evaluations of more than fifteen state-of-the-art models, in both zero-shot and fine-tuned settings, reveal pronounced modality gaps, unstable level-wise performance, and challenges in maintaining multilevel correctness. Fine-tuning substantially improves results across modalities while preserving general knowledge, positioning MSU-Bench as a robust foundation for future research in multimodal reasoning. To facilitate further research, we publicly release MSU-Bench and all associated resources.