📰 AI News

10,465 articles · Updated every 3 hours

arXiv:2603.25133v1 Announce Type: new Abstract: Rubric-based evaluation has become a prevailing paradigm for evaluating instruction following in large language

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

UniAI-GraphRAG: Synergizing Ontology-Guided Extraction, Multi-Dimensional Clustering, and Dual-Channel Fusion for Robust Multi-Hop Reasoning

arXiv:2603.25152v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries

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

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

arXiv:2603.25158v1 Announce Type: new Abstract: Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks.

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

The Competence Shadow: Theory and Bounds of AI Assistance in Safety Engineering

arXiv:2603.25197v1 Announce Type: new Abstract: As AI assistants become integrated into safety engineering workflows for Physical AI systems, a critical questio

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

Probabilistic Abstract Interpretation on Neural Networks via Grids Approximation

arXiv:2603.25266v1 Announce Type: new Abstract: Probabilistic abstract interpretation is a theory used to extract particular properties of a computer program wh

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

Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis

arXiv:2603.25273v1 Announce Type: new Abstract: The probabilistic abstract interpretation framework of neural network analysis analyzes a neural network by anal

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

A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion

arXiv:2603.25283v1 Announce Type: new Abstract: Gait is increasingly recognized as a vital sign, yet current approaches treat it as a symptom of specific pathol

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

SliderQuant: Accurate Post-Training Quantization for LLMs

arXiv:2603.25284v1 Announce Type: new Abstract: In this paper, we address post-training quantization (PTQ) for large language models (LLMs) from an overlooked p

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

DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers

arXiv:2603.25293v1 Announce Type: new Abstract: Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical dom

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

Evaluating Language Models for Harmful Manipulation

arXiv:2603.25326v1 Announce Type: new Abstract: Interest in the concept of AI-driven harmful manipulation is growing, yet current approaches to evaluating it ar

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

Macroscopic Characteristics of Mixed Traffic Flow with Deep Reinforcement Learning Based Automated and Human-Driven Vehicles

arXiv:2603.25328v1 Announce Type: new Abstract: Automated Vehicle (AV) control in mixed traffic, where AVs coexist with human-driven vehicles, poses significant

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

Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous Decision Making in Sustainable and Resilient Industrial Networks

arXiv:2603.25334v1 Announce Type: new Abstract: Distributed intelligence in industrial networks increasingly integrates sensing, communication, and computation

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

4OPS: Structural Difficulty Modeling in Integer Arithmetic Puzzles

arXiv:2603.25356v1 Announce Type: new Abstract: Arithmetic puzzle games provide a controlled setting for studying difficulty in mathematical reasoning tasks, a

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

Does Structured Intent Representation Generalize? A Cross-Language, Cross-Model Empirical Study of 5W3H Prompting

arXiv:2603.25379v1 Announce Type: new Abstract: Does structured intent representation generalize across languages and models? We study PPS (Prompt Protocol Spec

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

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models

arXiv:2603.25412v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on explicit chain-of-thought (CoT) reasoning to solve complex tas

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

Modernising Reinforcement Learning-Based Navigation for Embodied Semantic Scene Graph Generation

arXiv:2603.25415v1 Announce Type: new Abstract: Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond pure

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

Cross-Model Disagreement as a Label-Free Correctness Signal

arXiv:2603.25450v1 Announce Type: new Abstract: Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deploym

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

Retraining as Approximate Bayesian Inference

arXiv:2603.25480v1 Announce Type: new Abstract: Model retraining is usually treated as an ongoing maintenance task. But as Harrison Katz now argues, retraining

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

EcoThink: A Green Adaptive Inference Framework for Sustainable and Accessible Agents

arXiv:2603.25498v1 Announce Type: new Abstract: As the Web transitions from static retrieval to generative interaction, the escalating environmental footprint o

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

Voxtral TTS

arXiv:2603.25551v1 Announce Type: new Abstract: We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as

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

Is Mathematical Problem-Solving Expertise in Large Language Models Associated with Assessment Performance?

arXiv:2603.25633v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used in math education not only as problem solvers but also as ass

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

Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?

arXiv:2603.25719v1 Announce Type: new Abstract: We present an empirical study of how far general-purpose coding agents -- without hardware-specific training --

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

R-C2: Cycle-Consistent Reinforcement Learning Improves Multimodal Reasoning

arXiv:2603.25720v1 Announce Type: new Abstract: Robust perception and reasoning require consistency across sensory modalities. Yet current multimodal models oft

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

Back to Basics: Revisiting ASR in the Age of Voice Agents

arXiv:2603.25727v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems have achieved near-human accuracy on curated benchmarks, yet still fa