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
Terence Tao: Mathematics in the Age of AI [pdf]
陶哲轩巅峰视角：AI如何重塑数学研究的未来与方法，顶级数学家前沿思考
Article URL: https://teorth.github.io/tao-web/slides/age-of-ai-icm-2026.pdf Comments URL: https://news.ycombinator.com/item?id=49056620 Points: 1 # Co…
3
AI Virtue: What is "Good" Knowledge in the Age of Artificial Intelligence?
从553篇论文中透视AI时代“好知识”的定义，数字人文方法揭示认识论变迁。
arXiv:2607.01776v1 Announce Type: cross Abstract: In the age of AI, what will be good knowledge? This article, which is accepted and forthcoming in a …
4
SOLAR: AI-Powered Speed-of-Light Performance Analysis
用AI实现光速级性能分析，突破传统瓶颈，硬件优化新范式。
arXiv:2606.26383v1 Announce Type: cross Abstract: How fast could a deep-learning model run on target hardware, and how far is today's implementation f…
5
A global log for medical AI
一份面向医疗AI的全球日志体系，让关键的AI事件可追溯、可审计，理解系统如何记录与复现。
arXiv:2510.04033v2 Announce Type: replace Abstract: Modern computer systems rely on syslog, a universal protocol that records critical events across h…
6
Rubric-as-Experts: Case-Specific MQM Rubrics for Translation Quality Evaluation
翻译质量评估新范式：让AI按具体案例定制评估标准，比通用质检更精准
arXiv:2606.21559v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential in fine-grained translation quality evaluatio…
7
Order Is Not Control
52页论文探讨秩序与控制间微妙关系，挑战传统认知的复杂系统理论新视角
arXiv:2606.12923v1 Announce Type: cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing ob…
8
What Uncertainties Do We Need for Dynamical Systems?
动力系统的不确定性研究，最新 arXiv 论文探讨关键问题。
arXiv:2606.11988v1 Announce Type: new Abstract: The distinction between aleatoric and epistemic uncertainty has received considerable attention in mac…
9
CoCoSI: Collaborative Cognitive Map Construction for Spatial Intelligence
新框架CoCoSI让多个智能体协作构建认知地图，突破空间智能瓶颈
arXiv:2606.10401v1 Announce Type: new Abstract: Spatial intelligence is a key frontier for multimodal large language models (MLLMs), enabling them to …
10
Effective Reasoning Chains Reduce Intrinsic Dimensionality
推理链越长越聪明？新研究揭示有效推理链能显著降低任务的内在维度，ICML spotlight论文值得关注。
arXiv:2602.09276v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning and its variants have substantially improved the performanc…
11
Generating Robust Portfolios of Optimization Models using Large Language Models
用大语言模型自动生成优化模型组合，提升稳健性，ICML 研讨会论文揭示前沿思路。
arXiv:2605.27013v1 Announce Type: new Abstract: Mathematical optimization is a powerful tool for structured decision-making across domains such as res…
12
CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly
提出自演化框架解决LLM网络安全智能体适应性难题，迭代优化策略突破固定脚手架局限。
arXiv:2605.26195v1 Announce Type: cross Abstract: LLM-based agents are increasingly used for cybersecurity tasks, but most existing systems rely on fi…