arXiv cs.CLOct 15, 2026Research
Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory WritingLangChainOct 15, 2026News
Context Engineering with Deep Agents: How To Remember Without Keeping Everything In ContextApple Machine LearningOct 15, 2026News
Plan or Retrieve First? A Scale Study of Tool Discovery ArchitecturesTogether AIOct 15, 2026News
Meta Muse Spark Open is live on Together AICrewAIOct 14, 2026Releases
CrewAI 1.15.28: Add crewai eval command to report where a stopped model brokeVercelOct 13, 2026News
Gemini 4 Argon now available on AI GatewayNetlifyOct 13, 2026News
Mistral Large 4 now available in Agent RunnersApple Machine LearningOct 12, 2026News
Self-Compacting Language Model AgentsLangChain · YouTubeOct 9, 2026Watch
What is a Skill?arXiv cs.CLOct 8, 2026Research
VFold: Symmetry-Aware Cross-Layer Value Cache CompressionArizeOct 8, 2026News
Cost Agent: find where your LLM and agent spend goes with your tracesarXiv cs.LGOct 7, 2026Research
RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement LearningClaude API Release NotesOct 7, 2026News
Claude Haiku 5.5arXiv cs.CLOct 7, 2026Research
Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollutionlangchain-aws (PyPI)Oct 6, 2026Releases
langchain-aws==1.8.1OpenRouterOct 6, 2026New Models
New model: Mistral: Mistral Large 4InfoQ · YouTubeOct 5, 2026Watch
Context Engineering for LLM Apps: What Worked, What Didn'tarXiv (vision, retrieval & HCI) cs.CVOct 1, 2026Research
MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video GenerationGrafana · YouTubeSep 30, 2026Watch
Context engineering fundamentals: How AI agents find what they need (The Context Window #6)arXiv cs.CLSep 30, 2026Research
Persistent Context Graphs for Efficient Memory Compaction in LLM Agents