Lacuna: A Research Map for Machine Learning

2026-06-24

AI Summary

This study addresses the fragmented and unstructured nature of knowledge in machine learning research by introducing the first knowledge graph system that supports traceable provenance links. The proposed framework leverages large language models to extract abstracts, core concepts, research directions, and technical proposals from academic papers and associated metadata, thereby constructing a searchable and interpretable research landscape. It integrates a multi-stage agent architecture and multimodal interfaces (Web/Markdown/MCP), along with the capability to automatically generate in-depth research reports. Evaluated on benchmarks such as LitSearch, the system significantly outperforms OpenScholar; furthermore, Lacuna Deep Research achieves higher citation F1 scores, precision, expert reference hit rates, and overall report quality ratings on ReportBench-ML.

Abstract

Lacuna is a research map for machine learning that uses LLMs to turn papers and scholarly metadata into markdown summaries, concept elements, research directions, and research proposals. Each item keeps links to the primary source records and papers that support it. We release the map with web, markdown, and MCP interfaces. Across LitSearch, Multi-XScience-CS/ML, and ScholarQA-CS-ML, Lacuna outperforms OpenScholar with the strongest gains on LitSearch retrieval (Recall@10 0.538 vs. 0.424 for OpenScholar v3). We also evaluate Lacuna Deep Research, a multi-stage report agent over the map, on 25 ReportBench-ML survey tasks: Lacuna Deep Research reaches 0.052 citation F1, 0.339 citation precision, 99 expert-reference hits, and 7.82/10 RACE report quality, while GPT-Researcher reaches 0.039 F1, 0.290 precision, 72 hits, and 5.24/10 RACE.

Problem

• machine learning
• research mapping
• literature retrieval
• scholarly metadata
• research synthesis

Innovation

• research mapping
• large language models
• structured scholarly summarization
• retrieval-augmented generation
• academic knowledge organization