The explosion of scientific literature has left researchers drowning in data, making it nearly impossible to find, evaluate, and synthesize relevant work quickly enough. A new open-source system called Paper Circle aims to solve this crisis by deploying a team of artificial intelligence agents that act as a dedicated research assistant. Instead of forcing humans to sift through thousands of documents manually, these agents autonomously hunt for papers, score their relevance, and organize findings into structured knowledge graphs. The system operates using two specialized pipelines: one that retrieves and ranks literature from multiple sources while ensuring diverse results, and another that breaks down individual papers into typed nodes like concepts, methods, experiments, and figures to enable deep analysis. This approach not only speeds up discovery but also allows for graph-aware question answering to verify how well a collection of papers covers a specific topic. Benchmarks show that using stronger agent models consistently improves hit rates and recall, proving that smarter AI teams can handle complex research tasks more effectively than ever before. Researchers can now access the system online and download the code to build their own custom workflows for academic discovery. Source: Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework by Komal Kumar, Aman Chadha, Salman Khan, Fahad Shahbaz Khan, Hisham Cholakkal, https://arxiv.org/abs/2604.06170