ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915478063022080 |
|---|---|
| author | Chen, Qi Wei, Jingxuan Yao, Zhuoya Wang, Haiguang Wu, Gaowei Yu, Bihui Li, Siyuan Tan, Cheng |
| author_facet | Chen, Qi Wei, Jingxuan Yao, Zhuoya Wang, Haiguang Wu, Gaowei Yu, Bihui Li, Siyuan Tan, Cheng |
| contents | Understanding how scientific ideas evolve requires more than summarizing individual papers-it demands structured, cross-document reasoning over thematically related research. In this work, we formalize multi-document scientific inference, a new task that extracts and aligns motivation, methodology, and experimental results across related papers to reconstruct research development chains. This task introduces key challenges, including temporally aligning loosely structured methods and standardizing heterogeneous experimental tables. We present ResearchPulse, an agent-based framework that integrates instruction planning, scientific content extraction, and structured visualization. It consists of three coordinated agents: a Plan Agent for task decomposition, a Mmap-Agent that constructs motivation-method mind maps, and a Lchart-Agent that synthesizes experimental line charts. To support this task, we introduce ResearchPulse-Bench, a citation-aware benchmark of annotated paper clusters. Experiments show that our system, despite using 7B-scale agents, consistently outperforms strong baselines like GPT-4o in semantic alignment, structural consistency, and visual fidelity. The dataset are available in https://huggingface.co/datasets/ResearchPulse/ResearchPulse-Bench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03565 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference Chen, Qi Wei, Jingxuan Yao, Zhuoya Wang, Haiguang Wu, Gaowei Yu, Bihui Li, Siyuan Tan, Cheng Computation and Language Multimedia Understanding how scientific ideas evolve requires more than summarizing individual papers-it demands structured, cross-document reasoning over thematically related research. In this work, we formalize multi-document scientific inference, a new task that extracts and aligns motivation, methodology, and experimental results across related papers to reconstruct research development chains. This task introduces key challenges, including temporally aligning loosely structured methods and standardizing heterogeneous experimental tables. We present ResearchPulse, an agent-based framework that integrates instruction planning, scientific content extraction, and structured visualization. It consists of three coordinated agents: a Plan Agent for task decomposition, a Mmap-Agent that constructs motivation-method mind maps, and a Lchart-Agent that synthesizes experimental line charts. To support this task, we introduce ResearchPulse-Bench, a citation-aware benchmark of annotated paper clusters. Experiments show that our system, despite using 7B-scale agents, consistently outperforms strong baselines like GPT-4o in semantic alignment, structural consistency, and visual fidelity. The dataset are available in https://huggingface.co/datasets/ResearchPulse/ResearchPulse-Bench. |
| title | ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference |
| topic | Computation and Language Multimedia |
| url | https://arxiv.org/abs/2509.03565 |