PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917223549894656 |
|---|---|
| author | Burgess, James Hansen, Jan N. Peng, Duo Zhang, Yuhui Lozano, Alejandro Sun, Min Woo Lundberg, Emma Yeung-Levy, Serena |
| author_facet | Burgess, James Hansen, Jan N. Peng, Duo Zhang, Yuhui Lozano, Alejandro Sun, Min Woo Lundberg, Emma Yeung-Levy, Serena |
| contents | Search agents are language models (LMs) that reason and search knowledge bases (or the web) to answer questions; recent methods supervise only the final answer accuracy using reinforcement learning with verifiable rewards (RLVR). Most RLVR search agents tackle general-domain QA, which limits their relevance to technical AI systems in science, engineering, and medicine. In this work we propose training agents to search and reason over scientific papers -- this tests technical question-answering, it is directly relevant to real scientists, and the capabilities will be crucial to future AI Scientist systems. Concretely, we release a search corpus of 16 million biomedical paper abstracts and construct a challenging factoid QA dataset called PaperSearchQA with 60k samples answerable from the corpus, along with benchmarks. We train search agents in this environment to outperform non-RL retrieval baselines; we also perform further quantitative analysis and observe interesting agent behaviors like planning, reasoning, and self-verification. Our corpus, datasets, and benchmarks are usable with the popular Search-R1 codebase for RLVR training and released on https://huggingface.co/collections/jmhb/papersearchqa. Finally, our data creation methods are scalable and easily extendable to other scientific domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18207 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR Burgess, James Hansen, Jan N. Peng, Duo Zhang, Yuhui Lozano, Alejandro Sun, Min Woo Lundberg, Emma Yeung-Levy, Serena Machine Learning Artificial Intelligence Computation and Language Information Retrieval Search agents are language models (LMs) that reason and search knowledge bases (or the web) to answer questions; recent methods supervise only the final answer accuracy using reinforcement learning with verifiable rewards (RLVR). Most RLVR search agents tackle general-domain QA, which limits their relevance to technical AI systems in science, engineering, and medicine. In this work we propose training agents to search and reason over scientific papers -- this tests technical question-answering, it is directly relevant to real scientists, and the capabilities will be crucial to future AI Scientist systems. Concretely, we release a search corpus of 16 million biomedical paper abstracts and construct a challenging factoid QA dataset called PaperSearchQA with 60k samples answerable from the corpus, along with benchmarks. We train search agents in this environment to outperform non-RL retrieval baselines; we also perform further quantitative analysis and observe interesting agent behaviors like planning, reasoning, and self-verification. Our corpus, datasets, and benchmarks are usable with the popular Search-R1 codebase for RLVR training and released on https://huggingface.co/collections/jmhb/papersearchqa. Finally, our data creation methods are scalable and easily extendable to other scientific domains. |
| title | PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR |
| topic | Machine Learning Artificial Intelligence Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2601.18207 |