PaSa: An LLM Agent for Comprehensive Academic Paper SearchACL 2025 (Main) ByteDance Seed Introduction 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 scholarly queries.
| Stars | 1,516 |
| Forks | 110 |
| Language | Python |
| Category | AI 工具 |
| License | Apache-2.0 |
| Quality Score | 36.3/100 |
| Open Issues | 22 |
| Last Updated | 2025-05-27 |
| Created | 2024-12-23 |
| Platforms | python |
| Est. Tokens | ~98k |
Explore other popular ai 工具 tools:
pasa is PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant referen. It is categorized as a AI 工具 with 1.5k GitHub stars.
pasa is primarily written in Python. It covers topics such as research.
You can find installation instructions and usage details in the pasa GitHub repository at github.com/bytedance/pasa. The project has 1.5k stars and 110 forks, indicating an active community.
pasa is released under the Apache-2.0 license, making it free to use and modify according to the license terms.