산업ENWired AI
Google Maps Gets Chatty With a New Gemini-Powered Interface
“Ask Maps,” rolling out today to Google Maps on mobile, lets you ask Gemini questions about locations and even to plan trips on your behalf.
AI 뉴스
AI 업계의 최신 소식을 빠르게 확인하세요.
산업ENThe Verge AI
Perplexity’s Personal Computer turns your spare Mac into an AI agent
Perplexity wants to be more than just an answer engine. On Wednesday, it launched Personal Computer, a new AI agent tool that can turn a spare Mac into a locally run AI system, pitching it as "a digital proxy for you.
연구ENArXiv AI
Agentic Control Center for Data Product Optimization
arXiv:2603.10133v1 Announce Type: new Abstract: Data products enable end users to gain greater insights about their data by providing supporting assets, such as example questionSQL pairs which can be answered using the data or views over the database tables.
연구ENArXiv AI
Hybrid Self-evolving Structured Memory for GUI Agents
arXiv:2603.10291v1 Announce Type: new Abstract: The remarkable progress of visionlanguage models VLMs has enabled GUI agents to interact with computers in a humanlike manner.
연구ENArXiv AI
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation
arXiv:2603.10359v1 Announce Type: new Abstract: Distilling reasoning capabilities from Large Reasoning Models LRMs into smaller models is typically constrained by the limitation of rejection sampling.
연구ENArXiv AI
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
arXiv:2603.10384v1 Announce Type: new Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics.
연구ENArXiv AI
Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities
arXiv:2603.10396v1 Announce Type: new Abstract: Despite the growing demand for eliciting uncertainty from large language models LLMs, empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques developed under the classical probabilistic...
연구ENArXiv AI
Resource-constrained Amazons chess decision framework integrating large language models and graph attention
arXiv:2603.10512v1 Announce Type: new Abstract: Artificial intelligence has advanced significantly through the development of intelligent gameplaying systems, providing rigorous testbeds for decisionmaking, strategic planning, and adaptive learning.
연구ENArXiv AI
IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs
arXiv:2603.10521v1 Announce Type: new Abstract: Instruction hierarchy IH defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trustordered policy for resolving instruction conflicts.
연구ENArXiv AI
Adaptive RAN Slicing Control via Reward-Free Self-Finetuning Agents
arXiv:2603.10564v1 Announce Type: new Abstract: The integration of Generative AI models into AInative network systems offers a transformative path toward achieving autonomous and adaptive control.
연구ENArXiv AI
CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents
arXiv:2603.10577v1 Announce Type: new Abstract: ComputerUse Agents CUAs are emerging as a new paradigm in humancomputer interaction, enabling autonomous execution of tasks in desktop environment by perceiving highlevel naturallanguage instructions.
연구ENArXiv AI
Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
arXiv:2603.10588v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards RLVR has achieved remarkable success in logical reasoning tasks, yet whether large language model LLM alignment requires fundamentally different approaches remains unclear.