AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2657
延迟
—
最新内容
当前时间
安全连接 OPERATIONAL

03 / ARTICLE LEDGER

关联文章

按发布时间倒序

  1. Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization 2026-03-05 · ARXIV
  2. AI Agent框架探秘：拆解 OpenHands（11）--- Runtime主要组件 2026-03-05 · JUEJIN
  3. A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development 2026-03-05 · ARXIV
  4. Building custom model provider for Strands Agents with LLMs hosted on SageMaker AI endpoints | Amazon Web Services 2026-03-05 · BLOGS_PODCASTS
  5. The L in "LLM" Stands for Lying 2026-03-05 · HACKER_NEWS
  6. 当人类知识学会自己奔跑--skill 2026-03-05 · JUEJIN
  7. 003：RAG 入门-LangChain 读取图片数据 2026-03-05 · JUEJIN
  8. Monitoring Emergent Reward Hacking During Generation via Internal Activations 2026-03-05 · ARXIV
  9. Hindsight Quality Prediction Experiments in Multi-Candidate Human-Post-Edited Machine Translation 2026-03-05 · ARXIV
  10. A “ChatGPT for spreadsheets” helps solve difficult engineering challenges faster 2026-03-04 · BLOGS_PODCASTS
  11. AI 代码审查工具链搭建：用 AST 解析 + LLM 实现自动化 Code Review 的前端工程方案 2026-03-04 · JUEJIN
  12. Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems 2026-03-04 · ARXIV
  13. Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection 2026-03-04 · ARXIV
  14. Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation 2026-03-04 · ARXIV
  15. Symbol-Equivariant Recurrent Reasoning Models 2026-03-03 · ARXIV
  16. Multi-Head Low-Rank Attention 2026-03-03 · ARXIV
  17. Agent Skill 是什么？一文讲透 Agent Skill 的设计与实现 2026-03-03 · JUEJIN
  18. 用 SQL 调大模型？Hologres + 百炼，让数据开发直接“对话”AI 2026-03-03 · JUEJIN
  19. Java开发者的大模型入门：LangChain4j组件全攻略（一） 2026-03-03 · JUEJIN
  20. MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains 2026-03-03 · ARXIV
  21. KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging 2026-03-03 · ARXIV
  22. Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact 2026-03-03 · ARXIV
  23. Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark 2026-03-03 · ARXIV
  24. Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization 2026-03-03 · ARXIV
  25. CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning 2026-03-03 · ARXIV
  26. BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning 2026-03-03 · ARXIV
  27. Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation 2026-03-02 · ARXIV
  28. Do LLMs Benefit From Their Own Words? 2026-03-02 · ARXIV
  29. DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science 2026-03-02 · ARXIV
  30. CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation 2026-03-02 · ARXIV
  31. Building specialized AI without sacrificing intelligence: Nova Forge data mixing in action | Amazon Web Services 2026-03-02 · BLOGS_PODCASTS
  32. Build a serverless conversational AI agent using Claude with LangGraph and managed MLflow on Amazon SageMaker AI | Amazon Web Services 2026-03-02 · BLOGS_PODCASTS
  33. 从入门到辞职｜从ChatGPT到OpenClaw，跟上智能时代的进化 2026-03-02 · JUEJIN
  34. Right-sizes LLM models to your system's RAM, CPU, and GPU 2026-03-02 · HACKER_NEWS
  35. Spring AI 实战：从零构建类 OpenClaw 的自主 Agent 2026-03-02 · JUEJIN
  36. SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems 2026-03-02 · ARXIV
  37. Ollama 入门指南：本地大模型实践 2026-03-02 · JUEJIN
  38. 推理平台全景 2026-03-01 · JUEJIN
  39. 轻松接入大语言模型API -04 2026-03-01 · JUEJIN
  40. The Science of Detecting LLM-Generated Text (2024) 2026-03-01 · HACKER_NEWS
  41. Deterministic Programming with LLMs 2026-03-01 · HACKER_NEWS
  42. 一天一个开源项目（第36篇）：EverMemOS - 跨 LLM 与平台的长时记忆 OS，让 Agent 会记忆更会推理 2026-02-28 · JUEJIN
  43. OpenClaw：开源AI助手平台的革命之路 2026-02-28 · JUEJIN
  44. 基于 Go 语言与 DeepSeek-V3 构建企业级自动化代码审计系统深度解析 2026-02-28 · JUEJIN
  45. 一文搞懂激活函数！ 2026-02-27 · JUEJIN
  46. Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction Dataset 2026-02-27 · ARXIV
  47. We gave terabytes of CI logs to an LLM 2026-02-27 · HACKER_NEWS
  48. Show HN: Badge that shows how well your codebase fits in an LLM's context window 2026-02-27 · HACKER_NEWS
  49. AI Agent框架探秘：拆解 OpenHands（9）--- AgentController 2026-02-27 · JUEJIN
  50. Dify 构建 FE 工作流：前端团队可复用 AI 工作流实战 2026-02-27 · JUEJIN