AI

AI News

발행 2026년 8월 16일

0

이 목록을 나라·회사·기술별로 요약하는 프롬프트가 현재 언어로 복사됩니다. Claude·ChatGPT 등 아무 AI에 붙여넣으세요.

2026-08-15 ~ 2026-08-15 · AI 주요 소식 80건. 제목을 누르면 원문으로 이동합니다.

날짜출처키워드제목

2026-08-15🇺🇸 MarkTechPostfine-tuningFine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3
2026-08-15🌐 arXiv cs.AILLMAgreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
2026-08-15

🌐 arXiv cs.AI

LLM

Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing

2026-08-15🌐 arXiv cs.AIAIPosition: We Need Practical AI Alignment Methods to Mirror Human Reasoning

2026-08-15🌐 arXiv cs.AILLMDon't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese

2026-08-15🌐 arXiv cs.AILLMLearning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization

2026-08-15🌐 arXiv cs.AIAIMindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents

2026-08-15🌐 arXiv cs.AILLM$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

2026-08-15🌐 arXiv cs.AIAIAuditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting

2026-08-15🌐 arXiv cs.AILLMDead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues

2026-08-15🌐 arXiv cs.AIagentSteerBench-Work: A Benchmark for Agent Steering at Action Boundaries

2026-08-15🌐 arXiv cs.AIAIDesigning AI Pipelines for Decision-Ready ITSM Intelligence

2026-08-15🌐 arXiv cs.AIagentLines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy

2026-08-15🌐 arXiv cs.AIRAGPrivacy-Preserving RAG by Concealing Sensitive Information from External LLMs

2026-08-15🌐 arXiv cs.AImultimodalThe Role of Natural Language Understanding in Multimodal Video-Based Dengue Diagnosis

2026-08-15🌐 arXiv cs.AILLMBeyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies

2026-08-15🌐 arXiv cs.AIagentSpatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence

2026-08-15🌐 arXiv cs.AIagentBeyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories

2026-08-15🌐 arXiv cs.AILLMPractice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents

2026-08-15🌐 arXiv cs.AIAIAI and Consumer Rights in India Working Paper

2026-08-15🌐 arXiv cs.AIagentAgent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence

2026-08-15🌐 arXiv cs.AIinferenceFlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving

2026-08-15🌐 arXiv cs.AIagentOGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways

2026-08-15🌐 arXiv cs.AIdiffusionFrom Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion

2026-08-15🌐 arXiv cs.AIagentBoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs

2026-08-15🌐 arXiv cs.AIAIExplanatory Engagement Under Rare Anomalous Failure: Asymptotic Rarity in Model Behavior (or: The Asymptotic AI)

2026-08-15🌐 arXiv cs.AIinferenceSPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference

2026-08-15🌐 arXiv cs.AILLMSkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents

2026-08-15🌐 arXiv cs.AILLMTeach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents

2026-08-15🌐 arXiv cs.AILLMTsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems

2026-08-15🌐 arXiv cs.AIagentCapability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test

2026-08-15🌐 arXiv cs.AIAISovereign by necessity? Frontier AI export controls, cyber security, and the limits of national AI capability

2026-08-15🌐 arXiv cs.AIAINAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space

2026-08-15🌐 arXiv cs.AILLMStateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems

2026-08-15🌐 arXiv cs.AILLMLLM-Guided Graph Generation for Structure-Based Local Improvement Methods

2026-08-15🌐 arXiv cs.AIAIRules or Character? Scaling Laws for AI Safety Design

2026-08-15🌐 arXiv cs.AItransformerJointly Predicting Courses and Grades Using a Transformer-Based Model

2026-08-15🌐 arXiv cs.AIRAGWho Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings

2026-08-15🌐 arXiv cs.AIAIBeyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development

2026-08-15🌐 arXiv cs.AIAIMARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination

2026-08-15🌐 arXiv cs.AIAIOmniScientist: An Omni-Modal Omni-Discipline AI Scientist

2026-08-15🌐 arXiv cs.AIAIThe AI Accountability Ecosystem in the Era of Language Models

2026-08-15🌐 arXiv cs.AILLMWhat Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict Forecasting

2026-08-15🌐 arXiv cs.AIAIWhy Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance

2026-08-15🌐 arXiv cs.AIAIWhen AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Models

2026-08-15🌐 arXiv cs.AILLMFrom Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks

2026-08-15🌐 arXiv cs.AIAIAssessment Design in the GenAI Era: The X1-X2-X3 Assessment Pattern for Testing Students' AI Literacy, Learning Outcomes, and Reflection

2026-08-15🌐 arXiv cs.AIAIWhy AI Governance Frameworks Are Hard to Adopt: A Role-Based Stress Test of the NIST AI RMF

2026-08-15🌐 arXiv cs.AIAIHumans are Missing from AI Coding Agent Research

2026-08-15🌐 arXiv cs.AIAIInteraction Readiness: A Framework for Building and Evaluating AI Agents in Human Roles

2026-08-15🌐 arXiv cs.AIAIFluctlightDB: A Memory Model of Data for AI Agents

2026-08-15🌐 arXiv cs.AImultimodalA Hierarchical Energy-Based Model for Multimodal Cognition

2026-08-15🌐 arXiv cs.AIAISpecification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review

2026-08-15🌐 arXiv cs.AIneuralSSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization

2026-08-15🌐 arXiv cs.AIAINot All Nudges Land: Behavioral Controllability and Elaboration Quality in AI-Supported Journaling

2026-08-15🌐 arXiv cs.AIneuralPredicting When Random Low-Dimensional Reparameterizations Train Neural Networks

2026-08-15🌐 arXiv cs.AILLMTracing Provenance and Detecting Tampering with Complementary LLM Watermarks

2026-08-15🌐 arXiv cs.AIagentSynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization

2026-08-15🌐 arXiv cs.AILLMCRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives

2026-08-15🌐 arXiv cs.AIagentPIPES: Securing Agent Perception with Provenance and Priors

2026-08-15🌐 arXiv cs.AIgenerativeFSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation

2026-08-15🌐 arXiv cs.AIAIFalsehood and Impossibility Are Different Directions in an AI's Representation of Language

2026-08-15🌐 arXiv cs.AIAISPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data

2026-08-15🌐 arXiv cs.AIagentLabels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation

2026-08-15🌐 arXiv cs.AILLMInFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers

2026-08-15🌐 arXiv cs.AILLMDiscovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference

2026-08-15🌐 arXiv cs.AILLMBeyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

2026-08-15🌐 arXiv cs.AIgenerativeGenerative Universal Multimodal Retrieval with Dual-role Identifiers

2026-08-15🌐 arXiv cs.AIAIStatic analysis-guided agentic AI translation enables Rust as a full stack bioinformatics language

2026-08-15🌐 arXiv cs.AIAIUniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations

2026-08-15🌐 arXiv cs.AIneuralSampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization

2026-08-15🌐 arXiv cs.AILLMLigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation

2026-08-15🌐 arXiv cs.AIinferenceLipCache: A Local Inference Proxy with Certified Caching for Edge Image Classification Service

2026-08-15🌐 arXiv cs.AIgenerativeGEM: A Generative Embedding Model Bridging Reasoning and Retrieval

2026-08-15🌐 arXiv cs.AIfine-tuningFollow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales

2026-08-15🌐 arXiv cs.AIdiffusionGeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transport

2026-08-15🌐 arXiv cs.AIgenerativeNovel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data

2026-08-15🌐 arXiv cs.AILLMKeep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services

2026-08-15🌐 arXiv cs.AIAITraining AI Scientists to Replicate Research

2026-08-15🌐 arXiv cs.AIAIHeterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks