The paper introduces PaperPilot, a multi-turn scientific literature search agent that treats search as workflow induction. Starting from an anchor paper and a user query, it builds an executable DAG of operators for keyword search, citation expansion, filtering, scoring, reranking, and evidence extraction. User feedback updates both the query and the workflow. PaperPilot-9B reportedly improves over a base Qwen3.5-9B toolset agent, raising Hit@5 from 58.0 to 77.0, MRR from 47.5 to 59.4, and nDCG@10 from 26.8 to 32.5, while reducing workflow execution errors from 9.5% to 0%.
No heat snapshots are available in the last 24 hours.