Papers with Code adds Auto-Research category, 166 papers already tracked
NielsRogge · x · 2026-10-18
Niels Rogge added an Auto-Research task category to Papers with Code, now tracking 166 papers. The term, coined by Andrej Karpathy's autoresearch project, covers AI agents that autonomously run the full research loop—hypothesis, code edits, experiments, keep-or-discard decisions—judged by research progress rather than test passing, distinct from Deep Research Agents which only synthesize literature.
More from coding & agent
- Personal agents vs. websites that block them: real-phone computer use may win — lucasmeijer · 2026-10-18
- LSCBench: top AI coding agent passes 91.3% of tests but only 25.1% ship securely — krishnan · 2026-10-18
- AI-driven compiler optimization spree: JSON.parse up to 2.9x faster, shift now linear — cramforce · 2026-10-18
- Use Claude to recursively optimize deps for native tsc — original types are on GitHub — cramforce · 2026-10-18
- Claude Code shows fake summarized thinking as assistant messages — ~37% of transcript — Sauers_ · 2026-10-18
- Dev builds a demon-summoning TUI for managing AI agents — voidwalker_com · 2026-10-18