flashrsi
flashrsi is A Unified Framework for Efficient RSI Research. Contribute to RUC-NLPIR/FlashRSI development by creating an account on GitHub.. It is ranked #813 on the AI Radar, in AI research, first seen 6 days ago and shared in 2 posts (15.4k views).
GitHub - RUC-NLPIR/FlashRSI: A Unified Framework for Efficient RSI Research · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation FlashRSI Public Notifications You must be signed in to change notification settings Fork 1 ( 1 ) Star 57 ( 57 ) You must be signed in to star a repository About A Unified Framework for Efficient RSI…
What people said about flashrsi on X
🔥厉害了！仅需一行代码让 Agent 自己进化！FlashRSI 开源，RSI 研究终于不再“东一榔头西一棒”！ 人民大学 NLPIR 实验室刚放了个大招：FlashRSI 首个真正统一的递归自进化（RSI）研究框架。 以前复现一个算法、换个 Benchmark、对个 Harness 要翻好几个仓库，现在直接Algorithm × Benchmark × Harness，一键跑通。 核心亮点： 🔹12 种 RSI 算法一键复现（SkillOpt / OPRO / GEPA / ACE / RRSI / Meta-Harness 等全覆盖） 🔹30+ Benchmark + 多类 Datasets，统一实验流 🔹原生支持…
— @NFT_Chen, 6 days ago · 205 likes · see the post
RSI 这套方法有个公开的秘密：源任务上普遍涨，换到远域任务上普遍跌。 人大 RUC-NLPIR 开源了 FlashRSI，把 13 种 RSI 方法、30 个 benchmark、5 个 harness（Claude Code、Codex、MiniAgent、Pi、Hermes）收进一个接口，同一套配置里都能跑。 看它那张 Claude Code 的结果矩阵就很清楚。AppWorld 上 ADAS +25.00pp、SkillOpt +19.64pp、AHE +26.79pp；到了 far-OOD 的 DeepSearchQA，同一批方法变成 GEPA -14.00pp、ACE -12.00pp、ModularRSI…
— @qingke_ai, 5 days ago · 43 likes · see the post
Alternatives to flashrsi
- academy.dair.ai — Chat with Paper
- alphaXiv — Now on @askalphaxiv
- flashprove — Further progress in provable inference will likely be an important part of improving trust in AI deployment. To that…
- moe-blogpost — A hands-on guide to training Mixture-of-Experts models
- liberai.com — Technical blog
- Science's Last Exam — Can AI do research, end to end? Science's Last Exam defines and measures whether an AI agent can carry a research goal…
flashrsi in numbers
- Rank on the AI Radar: #813 of 10425
- Shared in 2 posts by 2 accounts: @NFT_Chen, @qingke_ai
- 15.4k views on those posts
- First seen 6 days ago, last shared 5 days ago
- Pricing seen by AGK Intelligence: open source
- Market: AI research
FAQ
What is flashrsi?
A Unified Framework for Efficient RSI Research. Contribute to RUC-NLPIR/FlashRSI development by creating an account on GitHub. It was first shared on X 6 days ago and is ranked #813 on the AI Radar.
Is flashrsi free?
It is open source.
Who shared flashrsi?
2 accounts on X, including @NFT_Chen, @qingke_ai, in 2 posts totalling 15.4k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.3k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 17:44 UTC. Full method.