Banger paper on RSI with foundation model systems.
This is a AI post classified by AGK Intelligence as AI research (research), kept by the AI Radar because it carries real work, not commentary.
Banger paper on RSI with foundation model systems. (bookmark it) Seriously, I highly recommend this paper if you want to start experimenting with RSI in your own company. Lots of great insights and tips. They propose Recursa, which raises DeepSeek-V4.1-Flash from 30.0% to 55.0% all-pass on held-out legal tasks, without a stronger teacher or human experts. The model weights stay the same. The gain comes from a knowledge repository the system writes for itself. The repository stores domain skills, instructions on when to use them, memories of past tasks, and reflections. Recursa first bui
Posted by elvis (328.1k followers) 1 days ago · 237 likes · 18.6k views · view the original post on X. Kept by the AI Radar as AI research. Tools mentioned: arXiv.org, academy.dair.ai.
More AI work like this
- Someone made a decision model write text with a vocabulary of just 254 tokens. — @RoundtableSpace
- alphaXiv 🤝 OpenResearch — @askalphaxiv
- Stanford just made learning how LLMs actually work a lot easier. — @EvanLuthra
- No need for me to manually scan for new model releases anymore, since @paperswithcodee… — @NielsRogge
- We’re introducing ToyBlocks, an open simulated tabletop for controlled experiments in… — @allen_ai
- HotBench - Expert-authored tasks in medicinal chemistry, microbiology and dermatology to… — @SynBio1
- I wonder if you realize how interesting this is. — @SciTechera
- 🔥我靠！终于有大公司把AI模型后训练的“魔法”拆成可复现配方了！ — @NFT_Chen
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.