From aa8c9c57ebb5170037925b235d99bec031f81d77 Mon Sep 17 00:00:00 2001 From: promptadmin Date: Wed, 22 Jul 2026 03:57:15 +0000 Subject: [PATCH] [upstream-sync] README.md from ai-boost/awesome-ai-for-science@43c134d3 [catalogue] --- .../ai-boost-awesome-ai-for-science/catalogue/README.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/upstream/ai-boost-awesome-ai-for-science/catalogue/README.md b/upstream/ai-boost-awesome-ai-for-science/catalogue/README.md index 130f7f9..f4e4f1d 100644 --- a/upstream/ai-boost-awesome-ai-for-science/catalogue/README.md +++ b/upstream/ai-boost-awesome-ai-for-science/catalogue/README.md @@ -2,9 +2,9 @@ title: "Readme" task: "" lineage_type: import -upstream_source: https://github.com/ai-boost/awesome-ai-for-science/blob/086e63bb/README.md -upstream_sha: 086e63bb -imported_at: 2026-07-19 +upstream_source: https://github.com/ai-boost/awesome-ai-for-science/blob/43c134d3/README.md +upstream_sha: 43c134d3 +imported_at: 2026-07-22 prompt_class: catalogue upstream_changes: accepted author: upstream @@ -144,6 +144,7 @@ validated: false - [Chat2Plot](https://github.com/nyanp/chat2plot) - Secure text-to-visualization through standardized chart specifications - [AutoViz](https://github.com/AutoViML/AutoViz) - Automated data visualization with minimal code - [PlotlyAI](https://plotly.com/ai/) - AI-powered data visualization and dashboard creation +- [Flint (Microsoft)](https://github.com/microsoft/flint-chart) - Visualization intermediate language that lets AI agents create expressive, polished charts from simple, human-editable specs, compiling the same input to 30+ chart types across Vega-Lite, ECharts, and Chart.js with an MCP server for agent integration (1.9K+ stars, MIT License, 2026) --- @@ -292,6 +293,7 @@ validated: false - [ARA (Agent-Native Research Artifact)](https://github.com/ARA-Labs/Agent-Native-Research-Artifact) - Research ecosystem for rigorous and trustworthy AI scientists — a protocol and skill bundle that makes autonomous research verifiable, crystallized, and observable through structured, machine-executable research artifacts and five agent skills for research management, compilation, verification, visualization, and publication (ARA-Labs, 447+ stars, MIT License, 2026) - [Scholar Loop](https://github.com/renee-jia/scholar-loop) - Autonomous multi-agent AI scientist that mirrors a PhD workflow: literature review → grounded hypothesis → real ML experiments → self-critique → write-up; features a deterministic harness with frozen-metric scoring, edit allowlists, and a verified registry to make reward-hacking and hallucination impossible, plus 108 unit tests runnable without API keys or GPUs (461+ stars, MIT License, 2026) - [ResearchStudio (Microsoft)](https://github.com/microsoft/ResearchStudio) - AI co-author covering the entire research lifecycle — from an under-specified research direction to a published paper; includes ResearchStudio-Idea for evidence-grounded research ideation and ResearchStudio-Reel for turning finished papers into posters, narrated videos, blogs, and interactive reels; runs as skills on Claude Code and Codex (1.2K+ stars, MIT License, 2026) +- [Principia](https://github.com/pzqpzq/Principia) - Principle-first scientific idea discovery framework that extracts reusable principles from public literature and private research materials, composes them into traceable Idea Cards with prior-art comparisons, and exports validation-ready research packs; emphasizes inspectable scientific objects, risk disclosure, and falsification paths (ICML 2026, 411+ stars, MIT License) ### Evaluation & Benchmarking - [ScienceAgentBench (ICLR 2025)](https://github.com/OSU-NLP-Group/ScienceAgentBench) - 102 executable tasks from 44 peer-reviewed papers across 4 disciplines with containerized evaluation @@ -305,6 +307,7 @@ validated: false - [SciBench](https://arxiv.org/abs/2307.10635) - College-level scientific problem-solving evaluation across multiple domains - [NewtonBench (ICLR 2026)](https://github.com/HKUST-KnowComp/NewtonBench) - 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) - [ResearchClawBench (InternScience, arXiv 2026)](https://github.com/InternScience/ResearchClawBench) - 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) +- [Terminal-Bench Science (Harbor Framework, 2026)](https://github.com/harbor-framework/terminal-bench-science) - 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) ### Academic Review & Evaluation - [AgentReview](https://agentreview.github.io/) - LLM agents simulating academic peer review ecosystems -- 2.54.0