1
Recursive Synthesis for Long-Horizon Terminal Tasks
面向长时程终端任务，递归合成方法带来全新解决思路，值得关注。
arXiv:2608.05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hun…
2
Out-Of-The-Loop Multi-Fidelity Bayesian Optimization
跳出循环的隐式监督，多保真贝叶斯优化迎来新范式，降本增效直击采样痛点。
arXiv:2608.04113v1 Announce Type: cross Abstract: Black-box optimization is a ubiquitous problem in science and engineering, often dealing with expens…
3
Show HN: Proxy Block-CAGE, a new sparse block attention
提出一种新型稀疏块注意力机制Proxy Block-CAGE，有望提升长序列建模效率并降低计算开销。
Hi, I'm a PhD student in Bioinformatics/Computational Biology with a software engineering background, I'm trying to pivot toward AI/ML research. I'm f…
4
Directed evolution algorithm drives neural prediction
定向进化算法与神经网络融合，解锁预测新范式
arXiv:2512.01362v2 Announce Type: replace Abstract: Neural prediction offers a promising approach to forecasting the individual variability of neuroco…
5
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
多目标优化新方案：Chebyshev退火算法让智能体技能训练更高效，兼顾精度与泛化能力。
arXiv:2605.19330v1 Announce Type: cross Abstract: LLM agents organize behavior through skills - structured natural-language specifications governing h…