1
Where does the race to automate AI research end?
自动化AI研究竞赛的终局在哪？探讨其可能带来的风险与启示。
Article URL: https://simonlermen.substack.com/p/where-does-the-race-to-automate-ai Comments URL: https://news.ycombinator.com/item?id=48374492 Points:…
2
Where does the race to automate AI research end?
探讨AI研究自动化竞赛的终极归宿，引发对齐与失控的深思。
Article URL: https://www.lesswrong.com/posts/gkbet5Gp7eoAE9bjY/where-does-the-race-to-automate-ai-research-end Comments URL: https://news.ycombinator.…
3
Principle-Evolvable Scientific Discovery via Uncertainty Minimization
LLM科学智能体新范式：通过不确定性最小化动态演化假设空间，突破静态先验限制，提升发现效率与创新性。
arXiv:2602.06448v2 Announce Type: replace Abstract: Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they…
4
Harnessing AtomisticSkills for Agentic Atomistic Research
原子级研究新范式：AI代理结合AtomisticSkills，自动化材料科学探索。
arXiv:2605.24002v1 Announce Type: cross Abstract: Computational materials science and chemistry span vast knowledge domains and fractured software eco…
5
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
多智能体协同进化技能与记忆，实现个性化研究全流程自动化，直击“为谁自动化”的核心问题。
arXiv:2605.10813v2 Announce Type: replace Abstract: LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper…