PaperGuru (AutoTrustAI, 2026)

github.com/autotrustai/paperguru-benchmark
Active1.3Kupdated 1 month ago
TeX
NOASSERTION

Lifecycle-Aware Memory (LAM) primitive and benchmark for long-horizon research agents, achieving 65.95% mean reproduction on PaperBench and 94.66% on SurveyBench through Capital Chunk Memory (CCM) with versioned content, structural multi-hop relevance, and provenance-grounded composition; 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB (1.3K+ stars)

Sourced from

  • Awesome AI for Sciencegithub.com/autotrustai/paperguru-benchmark
  • GitHubgithub.com/autotrustai/paperguru-benchmark

Related resources

Benchmark evaluating AI agents on 75 curated Kaggle-style ML engineering competitions with reproducible Docker-based grading harness, human baselines, and end-to-end task lifecycle, used as a primary benchmark for autonomous ML research agents (e.g., InternAgent #1 at 36.44%)

Active1.6K3 months ago
Python
NOASSERTION

Benchmark evaluating AI agents' ability to replicate 20 ICML 2024 Spotlight/Oral papers from scratch, with 8,316 gradable tasks and author-co-developed rubrics

Active1.2K3 months ago
Python
MIT

Research coding benchmark curated by scientists with 338 subproblems across 16 subdomains (physics, math, materials, biology, chemistry), evaluating LLMs on realistic scientific programming tasks with gold-standard solutions (NeurIPS 2024)

Active2081 month ago
Python
Apache-2.0

Benchmark evaluating AI agents on complex real-world scientific workflows in terminal environments across life, physical, earth, and mathematical sciences; featured on model cards for Claude Opus 4.7, GPT-5.5, and Gemini 3.1 Pro (200+ stars, Apache 2.0)

Active2011 week ago
Python
Apache-2.0

Benchmark evaluating AI agents for end-to-end automated research from re-discovery to new-discovery, with 40 real-science tasks across 10 disciplines, curated datasets from published papers, and expert-curated multimodal rubrics (170+ stars, MIT License)

Active1721 month ago
Jupyter Notebook
MIT

First benchmark evaluating LLMs' ability to rediscover scientific laws through interactive experimentation across 324 tasks in 12 physics domains, featuring memorization-resistant metaphysical shifts of canonical laws (HKUST)

Active1525 months ago
Python
MIT