03 / ARTICLE LEDGER
关联文章
按发布时间倒序
- How we built an MCP bridge to give our AgentCore-hosted AI agent access to local MCP tools 2026-08-06 · BLOGS_PODCASTS
- Prime Agent: A self-improving RLM agent 2026-08-06 · HACKER_NEWS
- Can Large Language Models Recover Semantic Optimization Opportunities That Compilers Miss? 2026-08-06 · ARXIV
- From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking 2026-08-06 · BLOGS_PODCASTS
- Beating GPT-5.6 Sol on retrieval with 100x cheaper open models 2026-08-06 · HACKER_NEWS
- Assessment of Conditional Diffusion Model for Synthetic Histopathology Image Generation 2026-08-06 · ARXIV
- I'm Scared a Stranger Will Call My Novel AI, So I Built GitHub for Words 2026-08-06 · HACKER_NEWS
- Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation 2026-08-06 · ARXIV
- Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility 2026-08-06 · ARXIV
- Launch HN: HyperProbe (YC S26) – Agents that do read-only debugging in prod 2026-08-06 · HACKER_NEWS
- Circles powers telco personalization with OpenAI technology 2026-08-06 · BLOGS_PODCASTS
- PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents 2026-08-05 · ARXIV
- How we built a realtime system for responsive voice AI in six months 2026-08-05 · BLOGS_PODCASTS
- Cloudflare OS: an open platform for agents, apps, and work 2026-08-05 · HACKER_NEWS
- TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning 2026-08-05 · ARXIV
- Position: LLMs Can't Jump 2026-08-05 · HACKER_NEWS
- Inside our 353,000-person vibe coding course 2026-08-05 · BLOGS_PODCASTS
- WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournament 2026-08-05 · ARXIV
- Teaching AI to speak the language of pathology 2026-08-05 · BLOGS_PODCASTS
- Zero-Mem: Zero-Token Memory Operations for LLM Agents 2026-08-05 · HACKER_NEWS
- Unpacking ChatGPT Work: the Agent for a Billion Users 2026-08-05 · BLOGS_PODCASTS
- SocietyBench: Forecasting Counterfactual Social-World Evolution 2026-08-05 · ARXIV
- ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs 2026-08-05 · ARXIV
- [AINews] Megakernels are so dead and so back 2026-08-05 · BLOGS_PODCASTS
- Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection 2026-08-05 · ARXIV
- AI fuels more than half of cybercrime in Africa as scams surge – Interpol 2026-08-05 · HACKER_NEWS
- Third-party cyber evaluations involving OpenAI models 2026-08-05 · BLOGS_PODCASTS
- Mistral's Shieldstral: 3B open-weights model for multimodal moderation 2026-08-05 · HACKER_NEWS
- AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies 2026-08-05 · ARXIV
- Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality 2026-08-05 · ARXIV
- Apple says more ex-employees may have taken confidential data to OpenAI 2026-08-05 · HACKER_NEWS
- UEmbed: Unified Sparse and Dense Multimodal Embeddings 2026-08-04 · ARXIV
- LangGraph 状态机实战 2026-08-04 · JUEJIN
- Agent skills that bring team coding standards to Claude Code and Codex 2026-08-04 · HACKER_NEWS
- GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning 2026-08-04 · ARXIV
- Apple is getting this wrong 2026-08-04 · BLOGS_PODCASTS
- AI-Generated Images Discourage Me from Reading Your Blog 2026-08-04 · HACKER_NEWS
- 走进 AI Agent 2026-08-04 · JUEJIN
- The Condition-Number Barrier in Sparse Least Squares 2026-08-04 · ARXIV
- Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Framework 2026-08-04 · ARXIV
- [AINews] Qwen 3.8 Max(2.4T) and 27B, new open weights models for Coding and Cowork 2026-08-04 · BLOGS_PODCASTS
- AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling 2026-08-04 · ARXIV
- The Theoretical Foundation of Socratic Tests: Dynamic, Multimodal, Conversational Examinations 2026-08-04 · ARXIV
- The Inference Engineering Masterclass — Philip Kiely & Ali Taha, Baseten 2026-08-04 · BLOGS_PODCASTS
- LLMs reward expertise 2026-08-04 · HACKER_NEWS
- AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers 2026-08-04 · ARXIV
- Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents 2026-08-04 · HACKER_NEWS
- GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model 2026-08-04 · BLOGS_PODCASTS
- Development of FDD-ON: an Ontology for VAV HVAC System Fault Detection and Diagnostics 2026-08-04 · ARXIV
- What's the largest software project AI can complete on its own? 2026-08-04 · HACKER_NEWS