Multi-Turn Agentic Scientific Literature Search via Workflow Induction

2026-07-01

AI Summary

Scientific literature retrieval faces significant challenges due to users’ ambiguous, dynamically evolving, and preference-dependent intents. Existing approaches often lack controllability and optimizability owing to their reliance on fixed pipelines or implicit reasoning. To address this, this work proposes PaperPilot, the first framework to introduce an explicit, editable retrieval workflow mechanism. It models retrieval as a directed acyclic graph (DAG) constructed from anchor papers and user queries, supporting operations such as keyword search, citation expansion, filtering, scoring, re-ranking, and evidence extraction. The system iteratively refines both queries and workflow structure through user feedback. Built upon Qwen3.5-9B and integrating supervised imitation learning, preference optimization, and tool calling, PaperPilot achieves substantial improvements in Hit@5 (+19.0→77.0), MRR (+11.9→59.4), and nDCG@10 (+5.7→32.5), while reducing workflow execution errors to 0%.

Abstract

Scientific literature search often requires more than retrieving papers from a single query: users' intents are underspecified, preference-dependent, and evolve through interaction. Existing search agents typically rely on fixed pipelines or implicit language-only reasoning, making their search strategies difficult to control, inspect, and refine. We introduce PaperPilot, a multi-turn literature search agent that frames scientific search as workflow induction. Given an anchor paper and a user query, PaperPilot constructs an executable DAG of paper-search operators, including keyword search, citation expansion, filtering, scoring, reranking, and evidence extraction. User feedback is then used to refine both the query and the workflow itself. We train PaperPilot with supervised workflow imitation and preference optimization over controlled workflow corruptions. Experiments show that PaperPilot-9B improves over the base Qwen3.5-9B toolset agent under multi-turn interaction, increasing 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%. These results show that explicit, editable search workflows provide an effective and controllable interface for aligning literature search agents with complex scientific intent.

Problem

• scientific literature search
• multi-turn interaction
• search agent
• user intent
• workflow control

Innovation

• workflow induction
• multi-turn literature search
• search agent
• executable DAG
• preference optimization