Stop collecting random agent papers. Start with a research map.
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Stop collecting random agent papers. Start with a research map. Awesome AI4AI is a curated research catalog on long-horizon AI agents and recursive self-improvement for builders studying how AI systems can help improve AI. It helps you build a focused reading list by separating benchmarks, harness design, and model design, with paper and code links to follow when you want to dig deeper. Key features: • Three research tracks – browse evaluation, agent harnesses, and model-side methods separately • Newest-first collections – scan recent papers within each track instead of sorting a mixed rea
Posted by Dan Kornas (100.7k followers) 1 h ago · 8 likes · 578 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- TensorFold engine 1.2.1 is out. — @ashxhart
- 每天白送的 AI 额度，最容易被忘掉的反而是“签到”。 — @bkdgiffug
- 𝗛𝗲𝗿𝗺𝗲𝘀 Agent can turn a whole book into a skill. 📚🤯 — @BkashJosi
- DeepSeek just open-sourced a prototype that lets multiple AI coding agents work on… — @akshay81844
- Andrej Karpathy called YouTube "an enshittified wall of slop." — @heynavtoor
- huh? I am sorry @theo, but a model's intelligence is not why configured agents are a… — @jayleaton
- The next era of AI is agentic. — @alibaba_cloud
- new-term-radar 把 X、Hugging Face、GitHub 和网站新增页面里的信号整理成日报，适合找刚冒出来的模型、产品和项目名。 — @GitHub_Daily
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. 31.4k posts from 5k X accounts over the last 21 days, 9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-02 03:57 UTC. Full method.