#Harness Engineering

#Agents45#YouTube23#Developer Tools19#MCP18#RAG17#Reinforcement Learning16#Claude Code14#Retrieval14#Agent Evaluation13#Agent Skills13#MoE13#Multi-Agent Systems12#On-device AI12#Agent Systems11#Coding Agents11#Long Context11#Agent Harness10#Benchmark10#Multimodal10#Open Weights10#Tool Use10#VLM10#AI Engineer9#Agentic AI8#Codex8#OCR8#AI Agents7#Document Intelligence7#Embeddings7#Hugging Face7#NVIDIA7#Reasoning7#Vision-Language Models7#Agent Memory6#Agent Workflows6#arXiv6#Claude6#Computer Vision6#Context Engineering6#GRPO6#LoRA6#Model Training6#Qwen6#Qwen36#SKILL.md6#Agent Training5#AI for Science5#AI Safety5#Anthropic5#Edge AI5#Fine-tuning5#Foundation Models5#Observability5#Quantization5#Reranking5#RLVR5#Sparse Attention5#Synthetic Data5#Test-Time Scaling5#Data Pipeline4#Deep Research4#Gemma4#Image Generation4#Inference Optimization4#LLM Architecture4#LLM Evaluation4#LLM Systems4#Open Source4#Research Agents4#Training Systems4#Transformer4#Vector Search4#Video Generation4#VLA4#Workflow Automation4#Agent Runtime3#Agentic Coding3#AI Governance3#Auto Research3#AutoResearch3#Design Systems3#Distillation3#Document AI3#Evaluation Benchmark3#Google DeepMind3#Harness Engineering3#Inference Systems3#Knowledge Distillation3#KV Cache3#Liquid AI3#LLM Agents3#LLM Serving3#LLM Training3#MLOps3#Multi-Agent3#Object Detection3#Proactive Agents3#Prompt Engineering3#PyTorch3#Qwen3-VL3#Reasoning Models3#Robotics3#Security3#Self-Evolving Agents3#Small Language Models3#Sparse Models3#Structured Extraction3#Survey3#TDD3#Video Understanding3#World Model3#3D Reconstruction2#Agent Orchestration2#Agent OS2#Agent UI2#Agentic Search2#Apple Silicon2#Argilla2#Autonomous Driving2#Backpropagation2#BDD2#Blackwell2#Chain of Thought2#Context Management2#Continual Learning2#Contrastive Learning2#CUDA2#Data Curation2#Data Infrastructure2#DeepSeek2#Diffusion2#Diffusion LM2#DSPy2#Edge LLM2#Enterprise AI2#Evaluation2#ExecuTorch2#Gemini2#Gemma 42#Generative UI2#GEPA2#Hallucination2#Human-in-the-loop2#if(kakao)20202#Inference2#Information Retrieval2#Jenkins2#KakaoPay2#Knowledge Graph2#Korean LLM2#Kubernetes2#Language Modeling2#LFM2.52#LLM Pretraining2#LLM Reasoning2#LLMOps2#Local Agents2#Local-First2#LoCoMo2#Long-Horizon Agents2#LongMemEval2#Mechanistic Interpretability2#Memory Systems2#Metadata2#Microsoft Research2#MLX2#Mobile LLM2#Model Compression2#Multimodal Agents2#Multimodal AI2#Multimodal Embeddings2#Multimodal LLM2#Multimodal Models2#Nemotron2#NVFP42#Obsidian2#OpenAI2#Personal Agents2#Post-Training2#Privacy2#Product Strategy2#Prompt Optimization2#Quant Finance2#QUEST2#Recommender Systems2#Recursive Self-Improvement2#Research Engineering2#RF-DETR2#Roboflow2#SAM2#Skill Optimization2#Skills2#Small Object Detection2#Spatial Reasoning2#Speculative Decoding2#State Space Model2#Tabular Data2#Terminal-Bench2#Unsloth2#Verification2#Vibe Coding2#Vision Transformer2#Vision-Language Model2#vLLM2#2D Materials1#A-Evolve1#A/B Testing1#A2UI1#Accessibility1#Activation Steering1#Adobe Research1#AG-UI1#Agent Economy1#Agent Engineering1#Agent Protocols1#Agent Safety1#Agent Security1#AgentBench1#Agentic CLEAR1#Agentic Design1#Agentic LLMs1#Agentic Models1#Agentic Reasoning1#Agentic RL1#Agentic Security1#Agentic Self-Instruct1#Agentic Society1#AGI1#AI Co-Mathematician1#AI Coding1#AI Coding Agent1#AI Coding Agents1#AI Engineering1#AI for Mathematics1#AI Infrastructure1#AI Pricing1#AI Products1#AI SaaS1#AI-Q1#AKT-Rec1#Allen AI1#Altermagnetism1#Alyx1#Amazon Bedrock AgentCore1#AMD1#Analog Hardware1#ANN1#Antigravity1#Apple Intelligence1#AppWizzy1#AppWorld1#AR VR1#Arize1#ASI1#Assistive Technology1#Associative Memory1#Attention1#Attention Supervision1#Attractor Models1#Autodata1#Autogenesis1#AutoLab1#AutoML1#AutoResearchClaw1#BAGEL1#Baidu1#Benchmarks1#BES1#BI1#Biologically Plausible Learning1#Browser Agents1#Budget Forcing1#Calamari1#Calibration1#Camera Control1#Career1#Chunking1#CL-Bench1#Claude Opus1#Claw AI Lab1#Claw-Anything1#ClawHub1#CLEAR1#Clinical AI1#ClinSeekAgent1#Closed-loop Simulation1#Cloud VM1#Code Evolution1#Code Generation1#Code Intelligence1#Code Models1#Codex CLI1#Cognitive Loafing1#Computational Neuroscience1#Computer Use1#Computer Use Agent1#Computer-Use Agents1#Consulting1#Content Moderation1#Context Compression1#Context Distillation1#Context Graphs1#Context Learning1#Contextual Bandit1#Continuous Generation1#CopilotKit1#Cost Efficiency1#CPM.cu1#Criticality1#CSTS1#Ctx2Skill1#CUA-Gym1#Cucumber1#CUDA Graphs1#cuDNN1#CuTe DSL1#CyberGym1#D2Hub1#DA-Next1#Data Annotation1#Data Catalog1#Data Engine1#Data Sanitization1#Data Security1#Data-Centric AI1#Dataset Ops1#DCI-Agent1#Deep Search1#DeepEval1#DeepSeek-OCR1#DELEGATE-521#Delegated Work1#Delegation Intelligence1#Delivery1#Delta-Mem1#Demand-Driven Context1#Design Research1#Design Tools1#DESIGN.md1#Desktop Apps1#DevOps1#Diffusion Language Model1#Diffusion Language Models1#Diffusion LLM1#Diffusion Model1#Diffusion Transformer1#Direct Corpus Interaction1#Distilabel1#Distributed Training1#DKOS1#DNN Runtime1#Document Editing1#DPO1#DualOptim+1#Dynin-Omni1#EDA1#Edge Inference1#Effect1#Efficiency Frontier1#Efficient Coding1#Efficient Inference1#Egocentric Tracking1#Egress Control1#EHR1#EKS1#Elastic1#ElevenLabs1#ELF1#Embodiment1#Enactive AI1#Encoder-free1#Enterprise Agents1#Entropy1#ERNIE 4.51#ESOD1#ETL1#Evoflux1#Evolutionary Search1#EXAONE1#Fara-7B1#FastAPI1#FastEmbed1#FDS1#Ferrimagnetism1#Financial Time Series1#Fintech1#Fisher Information1#Fixed-point1#FLARE1#FlashAttention1#Flow Matching1#Flow-GRPO1#FluxMem1#Formal Mathematics1#Forward-Forward Algorithm1#Foundation Protocol1#FP4 Attention1#Fraud Detection1#Frontend AI1#FrontierMath1#GAIA1#Gemini Embedding 21#Gemini for Science1#GLM-5.21#Google Cloud1#Google I/O1#Governance1#GPT-5.51#GPU Optimization1#GQA1#Graph Network1#GraphRAG1#Grounding1#GroundX1#Guard Models1#Guardrail1#Guardrails1#GUI Agents1#Hallucination Detection1#Hardware Acceleration1#Harness Evolution1#Harness-11#HarnessAudit1#HarnessX1#HeavySkill1#Hermes Agent1#Hidden Problem Discovery1#Hidden-State Probing1#Historical Documents1#HNSW1#Hope1#Horizon Generalization1#HRM-Text1#Human Feedback1#Human Motion Tracking1#HumanLayer1#Hunyuan1#Hy-MT21#Hybrid Attention1#Hybrid SSM1#Hypernetworks1#Hyperparameter Transfer1#ICLR 20261#ifkakao1#ifkakao20201#Image Editing1#Image Inpainting1#Implicit Differentiation1#In-Context Learning1#Incremental Processing1#Inference Providers1#Inference Scaffolding1#Inference-Time Compute1#Inference-Time Feedback1#Inference-Time Reasoning1#Inference-Time Search1#Infrastructure as Code1#Inpainting1#Interpretability1#ITSM1#JaCoCo1#JAX1#Jina AI1#Kakao1#KakaoTalk1#Kanban1#Karpathy1#Kernel Optimization1#Keye-VL1#Kimi1#Knowledge Bases1#Knowledge Catalog1#Knowledge Graphs1#Knowledge Management1#KoHRM1#KOLongDoc1#Korean AI1#Korean VLM1#Kotest1#Kotlin1#Kronos1#LAMP1#Lance1#LangChain Deep Agents1#Latent Reasoning1#Latent Space1#Layout Analysis1#LazyCodex1#Leaderboard1#Lean1#LEAP1#Learning Rate Transfer1#Legacy Systems1#LFM21#License Compliance1#Life-Harness1#LightMem1#LiteLLM1#LiteVLA-H1#LLM Depth1#LLM Distillation1#LLM Fundamentals1#LLM Infrastructure1#LLM Internals1#LLM Ops1#LLM Safety1#LLM Wiki1#LM Programs1#Local AI1#Local Harness1#Local LLM1#Locally AI1#LocateAnything1#Logic Synthesis1#Long Document QA1#Long Video Understanding1#Long-Context Inference1#Long-Horizon1#Long-tail1#Long-Term Memory1#LongLive-2.01#Lookahead Reasoning1#Looped Transformers1#Macaron-A2UI1#Machine Translation1#Machine Unlearning1#Mamba1#Manifold Power Iteration1#Matrix Factorization1#Matt Pocock1#MaxText1#MCompassRAG1#MCP Apps1#MCTS1#MDASH1#Megatron-LM1#MemForest1#Memory Compression1#Memory-Augmented Generation1#Meta AI1#Meta-Optimization1#MetaAgent-X1#Microsoft1#Microsoft AI1#Microsoft Security1#Mid-Training1#MiMo1#Mind2Web1#MiniCPM-V1#MiniCPM41#MiniMax Sparse Attention1#MinT1#Mistral1#Mistral AI1#Mixture of Experts1#ML Engineering1#MLLM1#mmGRPO1#MMProLong1#Mobile Agents1#MobileLLM-R11#MobileMoE1#MockK1#Model Adaptation1#Model Pruning1#Model Studio1#Moderation1#ModernBERT1#Modular AI1#Moebius1#Monetization1#MongoDB1#Moonshot AI1#MTEB1#Multi-Agent Debate1#Multi-LoRA1#Multi-turn Evaluation1#Multi-View Reasoning1#Multilingual Retrieval1#Multimodal Diffusion1#Multimodal Reasoning1#Multimodal Retrieval1#Multimodal RL1#Multimodal Safety1#Multimodal Search1#Multimodal Training1#NanoGPT1#Native Unified Model1#Native VLM1#Natural Language Autoencoders1#NEO-unify1#Neo4j1#Nested Learning1#Netflix1#Neural Architecture Search1#Neural Networks1#NeurIPS 20251#nGPT1#NL-Refer1#NoisyAgent1#Normalized Transformer1#NVIDIA Cosmos1#NVIDIA NeMo1#OCR-Memory1#OKF1#OLIVE Platform1#Olympiad Math1#OmniDreams1#Omnimodal1#OmniShotCut1#OmO1#On-call1#On-policy Distillation1#OneManCompany1#OneVL1#Online Memory1#ONNX1#Open Knowledge Format1#Open Models1#Open Source Compliance1#Open Training Recipe1#OpenAI API1#OpenClaw-Skill1#OpenCompass1#OpenCV 51#OpenHarness1#OpenSearch-VL1#Optimizer1#Optimizers1#OSWorld1#Ouroboros1#PaddleOCR1#PaddleOCR-VL1#PageIndex1#Paper Reproduction1#ParaDLC-Bench1#Parallel Box Decoding1#Parallel Verification1#Parameter-Efficient Tuning1#Pare-Bench1#PEFT1#PerceptionDLM1#Personal Assistants1#Personalization1#Piccoma1#PII Detection1#Pixel Embeddings1#Platform Engineering1#Plugins1#PowerPoint1#PP-OCRv61#PrefixLM1#Preparedness1#Presentation AI1#Presentation Tools1#Priming1#PriorVLA1#ProAct1#Procedural Memory1#Procrustes Alignment1#Product1#Product Hunt1#Productivity1#Prometheus1#Prompt Tuning1#Protocols1#Pytest1#QAT1#Query Adaptation1#Query Rewriting1#Qwen-Image-2.01#Qwen2.5-VL1#Qwen3-Next1#R-SWA1#React1#Reasoning Model1#Recurrence1#Recursive Reasoning1#Region Captioning1#Reinforced Agent1#ReRe1#Research1#Research Workflow1#Residual Stream1#Richard Sutton1#Risk Assessment1#Risk Management1#RL Post-Training1#RMS1#Robot Learning1#Robust MLLM1#Robustness1#RoPE1#Ropedia1#Router1#Routing1#Runtime Systems1#Rust1#S-Agent1#Safety1#Safety Alignment1#SAHI1#SANA-WM1#Sandboxing1#Sandcastle1#SARIF1#Science Skills1#Scientific Discovery1#Search Agent1#SearchSwarm1#Segmentation1#Self-Consistency1#Self-Evolution1#Self-Generated Data1#Self-Harness1#Self-Improving Agents1#Self-Improving LLMs1#Self-Play1#Self-Speculation1#Self-Training1#Semantic ID1#Semantic Layer1#SemBridge1#SenseNova-U11#Sentence Transformers1#Sequence Classification1#SGLang1#Shot Boundary Detection1#Skill Evolution1#Skill Governance1#Skill Retrieval1#Skill-RAG1#SkillEvolBench1#Sliced Inference1#Sloppiness1#SmallCode1#Software Engineering1#Sparse Autoencoder1#Sparse Detection1#Sparse MoE1#Sparse Retrieval1#Spatial Foundation Models1#SpatialBench1#Specification First1#Speech1#Spintronics1#SPLADE1#SQL1#SRA-Bench1#State Tracking1#Static Analysis1#Storybook1#Streaming Data1#Stripe1#SU-011#Subterranean Agent1#Supply Chain Security1#Swarm Intelligence1#SWE-Bench1#SWIM1#Sycophancy1#TabEmbed1#TabPFN1#Talent Market1#TEDS1#Temporal Indexing1#Terraform1#Test Automation1#Test-Time Training1#Text Embeddings1#Text Rendering1#Text-to-SQL1#Thanos1#Theorem Proving1#Thought Templates1#ThriftAttention1#TIDE1#Time Series Forecasting1#TinyLoRA1#Token Classification1#Tokenizer1#Tool Calling1#Tool Selection1#Tool-Integrated Reasoning1#Tool-Using Agents1#Topic Modeling1#TorchAO1#Training Recipes1#Trajectory Audit1#Transformers1#Triton1#Tuna-21#TypeScript1#UI Engineering1#UI Inspiration1#UI over MCP1#UI Testing1#Uncertainty1#Unlimited-OCR1#Usage-Based Billing1#User Simulation1#Validation1#Valleytronics1#Vector Database1#VibeThinker-3B1#Video Editing1#Vision-Language Alignment1#Visual Grounding1#Visual Perception1#Visual Recovery1#Visual Regression1#VLM Agents1#Vulnerability Discovery1#WBench1#Web Agents1#WorkOS1#World Models1#X2SAM1#Z.AI1#ZeroEntropy1#Zyphra1#μP1

Agent Skills & Workflows

Learn Harness Engineering은 코딩 에이전트를 위한 ‘실행 환...

walkinglabs/learn-harness-engineering은 하네스 엔지니어링을 12개 강의, 6개 실습 프로젝트, 복사 가능한 템플릿과 harness-creator 스킬로 정리한 오픈소스 코스다. 프롬...

Sangmin Lee2026.06.15

Agent Skills & Workflows

AI Harness는 프롬프트를 더 세게 쓰는 대신 실행 환경을 설계하는 일이다

Tejas Kumar의 AI Engineer 발표는 낡은 GPT-3.5 Turbo 브라우저 에이전트가 Hacker News upvote task에서 실패하고 거짓 성공을 보고하는 장면을 출발점으로, tool re...

Sangmin Lee2026.05.19

Agent Skills & Workflows

Harness Engineering은 코딩 에이전트 시대의 소프트웨어 공학을 ‘...

OpenAI Ryan Lopopolo의 AI Engineer Europe 발표는 코드 작성이 싸진 뒤의 병목이 인간의 주의, 모델 컨텍스트, 검증 루프가 되며, 엔지니어의 역할이 에이전트가 일하기 좋은 하네스를...

Sangmin Lee2026.05.11