Paper Overview
Research area: NLP Authors: Komal Kumar, Aaman Chadha, Salman Khan Published: 2025-04-08 arXiv: 2504.06264
Original Abstract
The rapid growth of scientific literature has made it increasingly difficult for researchers to efficiently discover, evaluate, and synthesize relevant work. Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools. In this paper, we introduce Paper Circle, a multi-agent research discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature. The system comprises two complementary pipelines: (1) a Discovery Pipeline that integrates offline and online retrieval from multiple sources, multi-criteria scoring, diversity-aware ranking, and structured outputs; and (2) an Analysis Pipeline that transforms individual papers into structured knowledge graphs with typed nodes for concepts, methods, experiments, and figures, supporting graph-aware question answering and coverage verification. Both pipelines are implemented in an encoder-LLM-based multi-agent orchestration framework, producing fully reproducible, synchronized outputs (JSON, CSV, BibTeX, Markdown, and HTML) at every agent step.
Key Features
- Discovery Pipeline: offline and online multi-source retrieval, multi-criteria scoring, diversity-aware ranking, structured outputs
- Analysis Pipeline: per-paper structured knowledge graphs (concepts, methods, experiments, figures), graph-aware Q&A, coverage verification
- Reproducibility: synchronized JSON, CSV, BibTeX, Markdown, and HTML outputs at each agent step
Source: arXiv:2504.06264