# AIConfPaper API

> Semantic search over ~154,000 ACCEPTED AI-conference papers (NeurIPS, ICML, ICLR, CVPR, ECCV, ICCV, ACL, EMNLP, NAACL, COLING, CoRL, ICRA, IROS, RSS, AAAI, IJCAI, AISTATS, UAI; 2015-2026). Search papers by meaning, find similar papers, get citation counts, and get LaTeX-source download links. No authentication required.

Base URL: https://aiconfpaper.com

## Instructions for LLM Agents
- To learn the whole API in ONE fetch: `curl -fsSL https://aiconfpaper.com/llms-full.txt`. Do NOT scrape the HTML web UI.
- ALWAYS start with `GET /api/v1/search?q=...`. `q` is free text: keywords, a sentence, or an entire abstract — results are ranked by semantic (embedding) similarity, not keyword matching.
- Carry the `paper_id` from search results into `/papers/{id}` and `/papers/{id}/similar`.
- For a paper's LaTeX/TeX source, read `links.arxiv_src` from `GET /api/v1/papers/{id}`. It may be `null` on the first call (resolving in the background) — retry once.
- Errors are RFC 9457 `application/problem+json` with a `detail` recovery hint.

## Endpoints
- [Search papers](/llms-full.txt): `GET /api/v1/search` — rank papers by semantic similarity to a query (filters: venue, year, sort).
- [Paper detail](/llms-full.txt): `GET /api/v1/papers/{id}` — full abstract, BibTeX, live citation count, and `links.arxiv_src` (TeX).
- [Similar papers](/llms-full.txt): `GET /api/v1/papers/{id}/similar` — nearest neighbors of a paper in embedding space.
- [Facets](/llms-full.txt): `GET /api/v1/facets` — valid `venue`/`tier` filter values and the year range.

## Specs
- Full agent reference: /llms-full.txt
- OpenAPI 3.1 (machine contract): /openapi.json
- Interactive docs: /docs
- MCP server (tool-calling agents): /mcp