Exa Launches SOTA Research Paper Search API for AI Agents
ycombinator · x · 2026-07-23
Exa has launched a state-of-the-art search API for AI agents, covering over 300 million research papers and 30 million authors. The tool uses large-scale PDF OCR, fine-tuned embeddings, and knowledge graph algorithms to solve the low recall issues of traditional tools like Google Scholar.
Additionally, Exa released two new research paper benchmarks for developers to build upon, aiming to help agents comprehensively and accurately access scientific knowledge.
Related event: ExaAI Launches Semantic Search API for 300M+ Academic Papers(2 posts)→
More from coding & agent
- A code sketch imagines an agent that upgrades itself and swaps models on demand — irvinebroque · 2026-07-23
- Claude Code plus Pika’s Voxel-it skill turns a meetup photo into a Minecraft scene — ytjessie_ · 2026-07-23
- A $20 Ethernet link is enough for 39.7GB multi-node GPU inference — Chuyito · 2026-07-23
- OpenAI GPT-5.6 Sol helped solve 6 open Erdős problems in 5 days — Charuru · 2026-07-23
- ModelScope launches an MCP server for text-to-image generation with Qwen-Image — modelcontextprotocol · 2026-07-23
- AILANG Parse brings deterministic DOCX, PPTX, XLSX and PDF parsing to MCP — modelcontextprotocol · 2026-07-23