ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference
This addresses the challenge of structured reasoning across scientific papers for researchers, though it appears incremental as it builds on existing agent and extraction methods.
The paper tackles the problem of understanding scientific idea evolution by formalizing multi-document scientific inference to reconstruct research development chains, and presents ResearchPulse, an agent-based framework that outperforms strong baselines like GPT-4o in semantic alignment, structural consistency, and visual fidelity using 7B-scale agents.
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.