用LLM自动配置特征通道，实现闭环系统高效扩展，典型大模型系统级应用。
arXiv:2607.20516v1 Announce Type: cross Abstract: Promising initial results in closed-loop large-language-model-based channel-configuration search dem…
Acrab发布边缘AI芯片GELIX 1及个人AI系统Agent Box，同时欧盟重罚Google 8.9亿欧元，科技圈大事件速览。
欧盟委员会对 Google 处以总计 8.9 亿欧元罚款，Anthropic 扩大 Claude 语音模式支持范围。 查看全文
安谋科技联手瑞芯微、紫光展锐等超20家伙伴，发起开源AIOS联盟，聚焦AI模型与感知运控，重塑AI软硬件生态。
IT之家 7 月 19 日消息，安谋科技在 2026 世界人工智能大会期间宣布发起“开源 AIOS 联盟”，目前已吸引超 20 家生态伙伴入驻，涵盖芯片与 IP、大模型、AI 硬件、具身本体、软件方案、高校、科研等国内 AI 产学研全链路。 IT之家从安谋科技公众号了解到，开源 AIOS 系统聚焦 …
复合AI系统聚合能力的边界在哪？这篇论文给出理论答案，值得关注AI架构的开发者细读。
arXiv:2602.21556v2 Announce Type: replace Abstract: When designing compound AI systems, a common approach is to query multiple copies of the same mode…
多品牌AI系统实战经验，用现实教训告诉你AI不解决烂系统，附超万条提示词管理方法
One of the biggest misconceptions about AI is that every project is unique. At first glance, it certainly feels that way. One project is a chatbot. An…
多智能体LLM通信如何影响内部表征？这项研究提出BOUNDARY_SYNC度量体系，揭示耦合机制。
arXiv:2607.01600v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as communicating agents, does inter-agent communication c…
多智能体协作打造动态3D场景，AI内容生成迎来新范式
arXiv:2607.01766v1 Announce Type: new Abstract: LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but…
区分上下文工程与记忆工程，掌握智能体AI推理与记忆的关键差异，提升系统设计能力。
Article URL: https://machinelearningmastery.com/context-vs-memory-engineering-in-agentic-ai-systems/ Comments URL: https://news.ycombinator.com/item?i…
CaveAgent突破传统无状态LLM限制，打造有状态运行时操作器，为智能体注入持久记忆。
arXiv:2601.01569v4 Announce Type: replace Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems r…
为AI系统提供执行来源追踪的开源工具，提升模型行为可追溯性
Article URL: https://github.com/Therealdk8890/DProvenanceKitPython Comments URL: https://news.ycombinator.com/item?id=48743043 Points: 1 # Comments: 0
用大语言模型革新张量分析，让复杂数据既“可操作”又“可解释”——AI与数学的深度碰撞。
arXiv:2606.28708v1 Announce Type: cross Abstract: Accurately explaining hidden patterns in multi-aspect data has typically been done by leveraging lab…
揭秘深度学习规模化的系统工程关键，C++/CUDA框架如何重塑训练性能与数值精度，值得技术人深读。
arXiv:2606.24780v1 Announce Type: new Abstract: Progress in deep learning is, at scale, more a matter of systems engineering than of modelling: the be…
Anthropic刚收回Claude Fable 5，Sakana转身用Fugu多模型自动合成系统实现前沿性能，打脸来得太快。
Last night, the increasingly enterprise-focused AI startup Sakana launched Fugu , a multi-agent orchestration system that delivers frontier-level AI p…
从技术角度全面梳理LLM Agent通信协议，为AI系统集成提供清晰框架。
arXiv:2606.19135v1 Announce Type: cross Abstract: As large language models (LLMs) advance and multi-agent systems aim to overcome the limits of standa…
自主AI系统行为不可预测，传统监控失效，本文揭示了如何通过可观测性深入洞察其内部运作。
Monitoring and Observability for Autonomous AI Systems Autonomous AI systems—from self-driving cars to algorithmic trading bots and robotic process au…
实测对比Agent记忆的推拉模式，开源项目帮你搞清楚哪个更适合你的AI系统。
Article URL: https://github.com/H-XX-D/recall-memory-substrate Comments URL: https://news.ycombinator.com/item?id=48580203 Points: 1 # Comments: 0
为智能体技能打造一个“活的”维基百科式知识基础设施，让AI技能持续演进与共享。
arXiv:2606.16523v1 Announce Type: new Abstract: While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an i…
探讨如何在最小监督下实现AI系统的不确定性感知治理，一篇前沿的学术新论。
arXiv:2606.15563v1 Announce Type: new Abstract: AI systems increasingly delegate decisions to specialized models, evaluators, tools, and supervisory c…
大模型与图数据深度融合，构建原生图协同AI系统，来自PAKDD前沿教程。
arXiv:2606.11560v1 Announce Type: cross Abstract: Large Language Models (LLMs) have advanced rapidly, but their limitations in structured and multi-ho…
用LLM自动生成GPU内核，突破AI系统性能瓶颈的前沿研究
arXiv:2601.15727v3 Announce Type: replace Abstract: The performance of modern AI systems is fundamentally constrained by the quality of their underlyi…