AI
AI News
발행 2026년 9월 12일
0
이 목록을 나라·회사·기술별로 요약하는 프롬프트가 현재 언어로 복사됩니다. Claude·ChatGPT 등 아무 AI에 붙여넣으세요.
2026-09-11 ~ 2026-09-12 · AI 주요 소식 80건. 제목을 누르면 원문으로 이동합니다.
날짜출처키워드제목
- 2026-09-12🇺🇸 MarkTechPostagentCan LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize
- 2026-09-12🇺🇸 MarkTechPostAnthropicAnthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No-Plugin Baseline, and a CI Gate for Skills
- 2026-09-11🇺🇸 MarkTechPostAISakana AI Launches Fugu Max and Fugu Ultra v2 for Cheaper, Stronger Multi-Agent Orchestration
- 2026-09-11🌐 arXiv cs.AIagentSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
- 2026-09-11🌐 arXiv cs.AIagentDo Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
- 2026-09-11🌐 arXiv cs.AIAIBlack-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery
- 2026-09-11🌐 arXiv cs.AILLMUnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
- 2026-09-11🌐 arXiv cs.AIAIAgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents
- 2026-09-11🌐 arXiv cs.AItransformerDecision Transformer for UAV-Mounted RIS-Assisted Dynamic D2D Communications
- 2026-09-11🌐 arXiv cs.AILLMAgent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather Alerts
- 2026-09-11🌐 arXiv cs.AImultimodalBeyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning
- 2026-09-11🌐 arXiv cs.AIagentWhat Should an Agent Forget? Separating What Is Stored from What Is Used
- 2026-09-11🌐 arXiv cs.AImultimodalAgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents
- 2026-09-11🌐 arXiv cs.AIinferenceDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts
- 2026-09-11🌐 arXiv cs.AIRAGIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
- 2026-09-11🌐 arXiv cs.AIAIVANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models
- 2026-09-11🌐 arXiv cs.AIAIAn Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
- 2026-09-11🌐 arXiv cs.AIneuralEfficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out Evaluation
- 2026-09-11🌐 arXiv cs.AIagentFrom Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls
- 2026-09-11🌐 arXiv cs.AImachine learningA Statistical Approach to Estimating Sample Size of Machine Learning Models
- 2026-09-11🌐 arXiv cs.AIfine-tuningArbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning
- 2026-09-11🌐 arXiv cs.AIdeep learningMyocardial Strain Drift Correction in Deep Learning Based Ultrasound Tracking
- 2026-09-11🌐 arXiv cs.AIneuralRouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian Splatting
- 2026-09-11🌐 arXiv cs.AIGPTLooped GPT-BERT: Trading Parameters for Computation in Small Language Modeling
- 2026-09-11🌐 arXiv cs.AIfine-tuningFine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?
- 2026-09-11🌐 arXiv cs.AIgenerativeuFlowCSP: Crystal Structure Prediction using Mean flow generative models
- 2026-09-11🌐 arXiv cs.AIinferenceSubgroup Membership Inference Audits of Differentially Private Synthetic Text
- 2026-09-11🌐 arXiv cs.AIfine-tuningActive Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
- 2026-09-11🌐 arXiv cs.AIAICan AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?
- 2026-09-11🌐 arXiv cs.AImultimodalOmniMed-FL: A Robust Multimodal Federated Learning Framework for Clinical Diagnosis
- 2026-09-11🌐 arXiv cs.AIAIIBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier
- 2026-09-11🌐 arXiv cs.AIagentMAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- 2026-09-11🌐 arXiv cs.AIagentNon-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and Remedies
- 2026-09-11🌐 arXiv cs.AILLMGrounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
- 2026-09-11🌐 arXiv cs.AIagentSelf-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control
- 2026-09-11🌐 arXiv cs.AImultimodalViSR-KGC: Visual Subgraph Reasoning with Vision-Language Models for Multimodal Knowledge Graph Completion
- 2026-09-11🌐 arXiv cs.AIAIPhysics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
- 2026-09-11🌐 arXiv cs.AIgenerativeDGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version
- 2026-09-11🌐 arXiv cs.AIneuralInstance-Aware Algorithm Selection for Maximum Clique via a Dual-Channel Graph Neural Architecture
- 2026-09-11🌐 arXiv cs.AIagentMADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
- 2026-09-11🌐 arXiv cs.AILLMFrom Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges
- 2026-09-11🌐 arXiv cs.AIAIMOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration
- 2026-09-11🌐 arXiv cs.AIAICognitive Amplification vs Cognitive Delegation in Human-AI Systems: A Metric Framework