No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by bytedance · Agent Tool · ★ 1.7k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pasa safe to install? View the security audit →
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. 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 sce
| Stars | 1,658 |
| Forks | 120 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 67.8954612102668/100 |
| Open Issues | 25 |
| Last Updated | 2025-05-27 |
| Created | 2024-12-23 |
| Platforms | python |
| Est. Tokens | ~98k |
Looking for a pasa alternative? If you're comparing pasa with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Model Context Protocol server for searching and analyzing arXiv papers
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies usi
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and g
🤖 An open-source, AI agent-native research canvas application that performs real-time search with HITL (Human
Explore other popular agent tool 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 Agent Tool with 1.7k 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 1.7k stars and 120 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.
The top alternatives to pasa on Agent Skills Hub include arxiv-mcp-server, company-research-agent, Deep-Research-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: