Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Abstract
paper pilot is a multi-turn literature search agent that uses executable workflows to improve search accuracy and reduce errors by incorporating user feedback and controlled workflow corruption training.
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.
Community

PaperPilot is a multi-turn research paper search agent for interactive literature discovery. It refines user queries, retrieves and reranks papers, and improves search workflows through agentic feedback. The paper also introduces a benchmark and training framework for evaluating paper-search agents, showing strong gains over standard retrieval baselines.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments (2026)
- SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents (2026)
- GrepSeek: Training Search Agents for Direct Corpus Interaction (2026)
- Towards Recursive Self-Evolving Agentic Literature Retrieval (2026)
- Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents (2026)
- Novelty-Aware Agentic Retrieval: Comparing Research Contributions Through Structured Multi-Step Reasoning (2026)
- APeB: Benchmarking Personalization Ability of Large Language Model Agents (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2607.00597 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper