LLM检索让广告推荐更稳定可预测，看论文如何用大模型优化推荐系统
arXiv:2605.21969v1 Announce Type: cross Abstract: Traditional ads recommendation systems have primarily focused on optimizing for prediction accuracy …
提出Agentic CLEAR框架，自动化评估LLM Agents多层次能力，提升评估效率与客观性。
arXiv:2605.22608v1 Announce Type: new Abstract: Agentic systems are becoming more capable: agents define strategies, take actions, and interact with d…
ACL 2026最新研究揭示LLM Agent在权力不对称对话中是否复现社会认知偏差，探索AI对话的公平性边界。
arXiv:2605.17694v1 Announce Type: new Abstract: Power differences shape human communication through well documented socio cognitive effects, including…
提出LLM智能体如何打破平台壁垒，重塑开放互联网生态。
arXiv:2506.23978v3 Announce Type: replace Abstract: While the Internet's core infrastructure was designed to be open and universal, today's applicatio…
GPT-5.5 驱动 Codex 在 NVIDIA 基础设施上运行，上万员工实测效率飙升，成本直降 35 倍
AI agents have revolutionized developer workflows, and their next frontier is knowledge work: processing information, solving complex problems, coming…
「未来式智能」获Pre-A轮融资，用灵搭平台打造数字劳动力工厂，自然语言生成工作流降低IT门槛。
文｜王欣逸 编辑｜邓咏仪 36氪获悉，未来式智能（AutoAgents.ai）近日完成Pre-A轮融资，新进投资方包括凡创资本、中关村资本、探元资本，老股东东证创新、麟阁创投跟投，本轮融资主要用于算力投入、团队扩张以及新产品的生态建设运营。 未来式智能成立于2023年6月，专注于以智能体技术赋能知识…
Redis作者分享LLM agents中EDIT工具的替代方案，实用技巧提升代码生成效率。
Article URL: https://antirez.com/news/166 Comments URL: https://news.ycombinator.com/item?id=48190359 Points: 5 # Comments: 1
LLM代理在信息获取中如何权衡成本与不确定性？新研究提出“校准-然后行动”方法，解决何时停止探索并提交答案的难题。
arXiv:2602.16699v3 Announce Type: replace Abstract: LLM agents are deployed in environments where they must interact to acquire information. In these …
用因果干预方法优化LLM代理长期记忆选择，告别语义相似度检索的局限性
arXiv:2605.17641v1 Announce Type: cross Abstract: Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet exist…
从排队论视角揭秘LLM推理的吞吐最优调度算法，为系统优化提供数学根基
arXiv:2504.07347v3 Announce Type: replace-cross Abstract: As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems f…
揭示LLM代理因记忆摘要隐藏毒性上下文的安全漏洞，记忆污染研究新发现
arXiv:2605.16746v1 Announce Type: cross Abstract: LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved contex…
提示注入是AI代理最致命的漏洞，研究表明现有防御手段可能永远无法彻底防范
arXiv:2605.17634v1 Announce Type: cross Abstract: Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, …
Vercel数据揭示Web基础设施正从手动配置走向AI代理驱动，30%部署由编码代理发起，代理时代加速到来。
From open source to a more powerful edge, see our predictions for the future of frontend development—featuring experts in React, Next.js, Svelte, and …
OpenAI 推出 Agents SDK 原生沙箱执行，助力构建安全长时运行的智能体应用。
OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agents across fi…
DevOps思维如何破解AI Agent开发瓶颈？从“改进基础设施”而非模型本身入手。
The Breakthrough That Changed How I Think About Agents Last night I watched a talk from AI.engineer that crystallized something I've been building tow…
首个专家策划的动态基准，专用于评估加密货币领域LLM Agent表现。
arXiv:2512.00417v5 Announce Type: replace Abstract: This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorou…
13个AI代理协同分析并购合同，跨9个专业领域，精确定位关键条款和引用，开源免费。
Article URL: https://github.com/zoharbabin/due-diligence-agents Comments URL: https://news.ycombinator.com/item?id=48170393 Points: 1 # Comments: 0
无需注册、无需API密钥，一条GET请求即可获取链接元数据，专为无法完成注册的AI智能体设计。
If you write code that calls links — a bot, a crawler, a RAG ingest job, an autonomous agent — you eventually need the metadata behind a URL: title, d…
Vercel Agent现在可通过AGENTS.md等文件自动应用项目编码指南，无需配置即可进行更精准的代码审查。
Vercel Agent now applies your repository’s coding guidelines during code reviews. Add an AGENTS.md file to your repository, or use existing formats li…
AI agent构建人人可做，但规模化运营需要专业平台，Vercel分享生产级部署的挑战与方案。
Prototyping is democratized, but production deployment isn't. AI models have commoditized code and agent generation, making it possible for anyone to …