yxc0433
·
2026-04-27
·
9 min
US-China Trade
中国3月份出口增长未达预期,进口激增为四年多来最大
China exports growth in March misses estimates, imports surge most in over four years
由于中东冲突打击了全球需求前景,,中国 3 月份出口增长降至六个月低点,而进口则录得最强劲...
China's export growth declined to a six-month low in March as the Middle East conflict hit global demand outlook, while imports logged their strongest...
01
Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel, Neel Patel, Majid Fekri, Tara Khani
·
2026-04-27
·
9 min
AI
Memanto: 类型化语义记忆与长视野智能体的信息理论检索
Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
从无状态语言模型推理到持久, 多会话自治代理的转变表明内存是主要架构...
The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectura...
02
Tharindu Kumarage, Lisa Bauer, Yao Ma, Dan Rosen, Yashasvi Raghavendra Guduri, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris
·
2026-04-27
·
7 min
AI
AI: 中的新兴战略推理风险:分类驱动的评估框架
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
随着推理能力和部署范围同步增长, 大型语言模型 (LLM) 获得了参与服务于自己的行为的能力......
As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own ...
03
Aofan Liu, Jingxiang Meng
·
2026-04-27
·
3 min
AI
作为反馈控制的自我校正: 误差动态, 稳定性阈值, 和法学硕士中的及时干预
Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs
迭代式自我修正越来越多地部署在代理 LLM 系统, 中,但重复细化是否会提高或降低性能仍然是一个问题。
Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains in...
04
yxc0433
·
2026-04-27
·
4 min
US-China Trade
中国称美国的封锁'危险且不负责任'
China calls U.S. blockade 'dangerous and irresponsible'
中国称美国封锁霍尔木兹海峡的伊朗港口是"危险且不负责任的行为",这将进一步加剧紧张局势......
China has called the U.S. blockade of Iranian ports in the Strait of Hormuz a "dangerous and irresponsible act" that will further enflame tensions in ...
05
Alberto Messina, Stefano Scotta
·
2026-04-27
·
9 min
AI
引入背景温度来表征大型语言模型中的隐藏随机性
Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
即使使用温度 $T=0$, 大型语言模型 (LLMs) 进行解码,也可以为相同的输入产生不同的输出。 Thinking Ma 的最新作品...
Even when decoding with temperature $T=0$, large language models (LLMs) can produce divergent outputs for identical inputs. Recent work by Thinking Ma...
06
Bulent Soykan, Gulsah Hancerliogullari Koksalmis, Hsin-Hsiung Huang, Laura J. Brattain
·
2026-04-27
·
3 min
AI
CognitiveTwin: 稳健的多模态数字双胞胎,用于预测阿尔茨海默的 疾病的认知衰退
CognitiveTwin: Robust Multi-Modal Digital Twins for Predicting Cognitive Decline in Alzheimer's Disease
由于疾病进展的异质性,预测阿尔茨海默的疾病(AD)的个体认知能力下降很困难。可靠的临床...
Predicting individual cognitive decline in Alzheimer's disease (AD) is difficult due to the heterogeneity of disease progression. Reliable clinical to...
07
Bin Wu, Arastun Mammadli, Xiaoyu Zhang, Emine Yilmaz
·
2026-04-27
·
10 min
AI
AgentSearchBench: AI 代理野外搜索基准
AgentSearchBench: A Benchmark for AI Agent Search in the Wild
AI 代理生态系统的快速发展正在改变复杂任务的委派和执行方式,,这为识别合适的任务带来了新的挑战……
The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable...
08
Zhengxu Yu, Yu Fu, Zhiyuan He, Yuxuan Huang, Lee Ka Yiu, Meng Fang, Weilin Luo, Jun Wang
·
2026-04-27
·
6 min
AI
从技能到人才: 将异构代理组织为现实世界的公司
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
通过模块化技能和工具集成,单个代理的能力迅速提高,,但多代理系统仍然受到固定...
Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed ...
09
yxc0433
·
2026-04-27
·
10 min
US-China Trade
伊朗战争:特朗普’霍尔木兹封锁考验美国与中国和印度的关系
Iran war: Trump’s Hormuz blockade tests U.S. ties with China and India
美国对霍尔木兹海峡的封锁不仅挤压了伊朗,还加大了对其两个最重要关系的压力……
The U.S. blockade of the Strait of Hormuz is not only squeezing Iran but also ratcheting up pressure on two of its most consequential relationships in...
10