📰 AI News

10,465 articles · Updated every 3 hours

arXiv:2603.24742v1 Announce Type: new Abstract: AI safety is an increasingly urgent concern as the capabilities and adoption of AI systems grow. Existing evolut

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach

arXiv:2603.24747v1 Announce Type: new Abstract: The emergence of large language model agents capable of invoking external tools has created urgent need for form

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Supervising Ralph Wiggum: Exploring a Metacognitive Co-Regulation Agentic AI Loop for Engineering Design

arXiv:2603.24768v1 Announce Type: new Abstract: The engineering design research community has studied agentic AI systems that use Large Language Model (LLM) age

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing

arXiv:2603.24787v1 Announce Type: new Abstract: Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) sys

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Resisting Humanization: Ethical Front-End Design Choices in AI for Sensitive Contexts

arXiv:2603.24853v1 Announce Type: new Abstract: Ethical debates in AI have primarily focused on back-end issues such as data governance, model training, and alg

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

SentinelAI: A Multi-Agent Framework for Structuring and Linking NG9-1-1 Emergency Incident Data

arXiv:2603.24856v1 Announce Type: new Abstract: Emergency response systems generate data from many agencies and systems. In practice, correlating and updating t

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning

arXiv:2603.24866v1 Announce Type: new Abstract: The physical world is not merely visual; it is governed by rigorous structural and procedural constraints. Yet,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

On the Foundations of Trustworthy Artificial Intelligence

arXiv:2603.24904v1 Announce Type: new Abstract: We prove that platform-deterministic inference is necessary and sufficient for trustworthy AI. We formalize this

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics

arXiv:2603.24929v1 Announce Type: new Abstract: Understanding and quantifying uncertainty in large language model (LLM) outputs is critical for reliable deploym

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Decoding Market Emotions in Cryptocurrency Tweets via Predictive Statement Classification with Machine Learning and Transformers

arXiv:2603.24933v1 Announce Type: new Abstract: The growing prominence of cryptocurrencies has triggered widespread public engagement and increased speculative

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol

arXiv:2603.24943v1 Announce Type: new Abstract: This paper introduces \textbf{FinMCP-Bench}, a novel benchmark for evaluating large language models (LLMs) in so

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Shopping with a Platform AI Assistant: Who Adopts, When in the Journey, and What For

arXiv:2603.24947v1 Announce Type: new Abstract: This paper provides some of the first large-scale descriptive evidence on how consumers adopt and use platform-e

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math

arXiv:2603.24961v1 Announce Type: new Abstract: Assessing student handwritten scratchwork is crucial for personalized educational feedback but presents unique c

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems

arXiv:2603.24963v1 Announce Type: new Abstract: Modern computational advertising platforms typically rely on recommendation systems to predict user responses, s

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

The Anatomy of Uncertainty in LLMs

arXiv:2603.24967v1 Announce Type: new Abstract: Understanding why a large language model (LLM) is uncertain about the response is important for their reliable d

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation

arXiv:2603.25001v1 Announce Type: new Abstract: Failure attribution is essential for diagnosing and improving multi-agent systems (MAS), yet existing benchmarks

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

A Public Theory of Distillation Resistance via Constraint-Coupled Reasoning Architectures

arXiv:2603.25022v1 Announce Type: new Abstract: Knowledge distillation, model extraction, and behavior transfer have become central concerns in frontier AI. The

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

System-Anchored Knee Estimation for Low-Cost Context Window Selection in PDE Forecasting

arXiv:2603.25025v1 Announce Type: new Abstract: Autoregressive neural PDE simulators predict the evolution of physical fields one step at a time from a finite h

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

From Stateless to Situated: Building a Psychological World for LLM-Based Emotional Support

arXiv:2603.25031v1 Announce Type: new Abstract: In psychological support and emotional companionship scenarios, the core limitation of large language models (LL

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Mechanistically Interpreting Compression in Vision-Language Models

arXiv:2603.25035v1 Announce Type: new Abstract: Compressed vision-language models (VLMs) are widely used to reduce memory and compute costs, making them a suita

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

MP-MoE: Matrix Profile-Guided Mixture of Experts for Precipitation Forecasting

arXiv:2603.25046v1 Announce Type: new Abstract: Precipitation forecasting remains a persistent challenge in tropical regions like Vietnam, where complex topogra

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Sparse Visual Thought Circuits in Vision-Language Models

arXiv:2603.25075v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE fea

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents

arXiv:2603.25097v1 Announce Type: new Abstract: Large Language Model based agents increasingly operate in high stakes, multi turn settings where factual groundi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

When Sensing Varies with Contexts: Context-as-Transform for Tactile Few-Shot Class-Incremental Learning

arXiv:2603.25115v1 Announce Type: new Abstract: Few-Shot Class-Incremental Learning (FSCIL) can be particularly susceptible to acquisition contexts with only a