PaSa: An LLM Agent for Comprehensive Academic Paper Search

TL;DR

PaSa is an LLM-powered agent designed for comprehensive academic paper search, outperforming existing methods in recall and precision on real-world queries despite being trained on synthetic data.

Contribution

Introduction of PaSa, a novel LLM-based academic paper search agent optimized with reinforcement learning and evaluated on real-world queries, demonstrating superior performance.

Findings

PaSa outperforms existing baselines in recall and precision.

PaSa-7B surpasses Google with GPT-4o by over 37% in recall@20.

PaSa trained on synthetic data generalizes well to real-world queries.

Abstract

We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholar queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academic queries to assess PaSa performance in more realistic scenarios. Despite being trained on synthetic data, PaSa significantly outperforms existing baselines on RealScholarQuery, including Google, Google Scholar, Google with GPT-4o for paraphrased queries, ChatGPT (search-enabled GPT-4o), GPT-o1, and PaSa-GPT-4o (PaSa implemented by prompting GPT-4o). Notably, PaSa-7B surpasses the best Google-based baseline, Google with GPT-4o, by 37.78% in recall@20 and 39.90% in recall@50, and exceeds PaSa-GPT-4o by 30.36% in recall and 4.25% in precision. Model, datasets, and code are available at https://github.com/bytedance/pasa.