1
Learning to Discover Iterative Spectral Algorithms
用机器学习自动发现迭代谱算法，突破人工设计瓶颈，开启算法发现新范式。
arXiv:2602.09530v2 Announce Type: replace-cross Abstract: We introduce AutoSpec, a neural network framework for discovering iterative spectral algorit…
2
Discovering Concept-Editing Algorithms with LLM Agents
用LLM Agent自动发现并优化概念编辑算法，为模型可解释性开辟新路径
Article URL: https://dmodel.ai/concept-erasure/ Comments URL: https://news.ycombinator.com/item?id=48746983 Points: 3 # Comments: 0
3
Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientist
用AI联合作者自主发现晶体结构预测新算法，开启材料科学智能探索新范式
arXiv:2606.22866v1 Announce Type: cross Abstract: We introduce Human-AI Co-discovery system (HACO) for scientific algorithm discovery through cross-do…
4
LLM-Guided Test-Time Discovery of Quantum-Chemical Approximation Algorithms
LLM在测试时引导量子化学近似算法发现，开创AI for Science新范式
arXiv:2606.20729v1 Announce Type: cross Abstract: Quantum chemistry simulations underpin modern materials discovery, yet their impact is limited by st…
5
Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems
提出GAMBLe分析框架，为AI驱动研究系统提供系统性评估方法，避免盲目探索。
arXiv:2606.02863v1 Announce Type: new Abstract: AI-Driven Research Systems (ADRS) -- systems coupling LLMs with automated evaluation to discover algor…
6
Effective Harness Engineering for Algorithm Discovery with Coding Agents
探索LLM与进化搜索结合时，执行基础设施设计对算法发现成功的关键影响，揭示三大工程设计问题。
arXiv:2605.15221v1 Announce Type: cross Abstract: AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) …