9,551 articles

📰 AI News

9,551 articles · Updated every 3 hours

All ⚡ AI Lessons (5768) ArXiv cs.AIForbes InnovationOpenAI NewsDev.to AIHugging Face BlogHackernoon
ArXiv cs.AI 📄 Paper 4h ago
InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI
arXiv:2604.04274v1 Announce Type: new Abstract: Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging becaus
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Preservation Is Not Enough for Width Growth: Regime-Sensitive Selection of Dense LM Warm Starts
arXiv:2604.04281v1 Announce Type: new Abstract: Width expansion offers a practical route to reuse smaller causal-language-model checkpoints, but selecting a wid
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence
arXiv:2604.04297v1 Announce Type: new Abstract: Physiological foundation models (FMs) have shown promise for biosignal representation learning, yet most remain
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
RESCORE: LLM-Driven Simulation Recovery in Control Systems Research Papers
arXiv:2604.04324v1 Announce Type: new Abstract: Reconstructing numerical simulations from control systems research papers is often hindered by underspecified pa
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Soft Tournament Equilibrium
arXiv:2604.04328v1 Announce Type: new Abstract: The evaluation of general-purpose artificial agents, particularly those based on large language models, presents
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Thermodynamic-Inspired Explainable GeoAI: Uncovering Regime-Dependent Mechanisms in Heterogeneous Spatial Systems
arXiv:2604.04339v1 Announce Type: new Abstract: Modeling spatial heterogeneity and associated critical transitions remains a fundamental challenge in geography
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Implementing surrogate goals for safer bargaining in LLM-based agents
arXiv:2604.04341v1 Announce Type: new Abstract: Surrogate goals have been proposed as a strategy for reducing risks from bargaining failures. A surrogate goal i
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Domain-Contextualized Inference: A Computable Graph Architecture for Explicit-Domain Reasoning
arXiv:2604.04344v1 Announce Type: new Abstract: We establish a computation-substrate-agnostic inference architecture in which domain is an explicit first-class
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets
arXiv:2604.04347v1 Announce Type: new Abstract: 2026 has brought an explosion of interest in LLM-guided evolution of agentic artifacts, with systems like GEPA a
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
REAM: Merging Improves Pruning of Experts in LLMs
arXiv:2604.04356v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) large language models (LLMs) are among the top-performing architectures. The largest mo
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Decocted Experience Improves Test-Time Inference in LLM Agents
arXiv:2604.04373v1 Announce Type: new Abstract: There is growing interest in improving LLMs without updating model parameters. One well-established direction is
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Optimizing Service Operations via LLM-Powered Multi-Agent Simulation
arXiv:2604.04383v1 Announce Type: new Abstract: Service system performance depends on how participants respond to design choices, but modeling these responses i
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Automatically Generating Hard Math Problems from Hypothesis-Driven Error Analysis
arXiv:2604.04386v1 Announce Type: new Abstract: Numerous math benchmarks exist to evaluate LLMs' mathematical capabilities. However, most involve extensive manu
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Gradual Cognitive Externalization: A Framework for Understanding How Ambient Intelligence Externalizes Human Cognition
arXiv:2604.04387v1 Announce Type: new Abstract: Developers are publishing AI agent skills that replicate a colleague's communication style, encode a supervisor'
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis
arXiv:2604.04399v1 Announce Type: new Abstract: Evaluating GUI agents presents a distinct challenge: trajectories are long, visually grounded, and open-ended, y
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
MolDA: Molecular Understanding and Generation via Large Language Diffusion Model
arXiv:2604.04403v1 Announce Type: new Abstract: Large Language Models (LLMs) have significantly advanced molecular discovery, but existing multimodal molecular
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems
arXiv:2604.04426v1 Announce Type: new Abstract: Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. Ho
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems
arXiv:2604.04448v1 Announce Type: new Abstract: Cognitive Behavioral Therapy (CBT) aims to identify and restructure automatic negative thoughts pertaining to in
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition
arXiv:2604.04456v1 Announce Type: new Abstract: Reliable pattern recognition systems should exhibit consistent behavior across similar inputs, and their explana
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
The Topology of Multimodal Fusion: Why Current Architectures Fail at Creative Cognition
arXiv:2604.04465v1 Announce Type: new Abstract: This paper identifies a structural limitation in current multimodal AI architectures that is topological rather
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
What Makes a Sale? Rethinking End-to-End Seller--Buyer Retail Dynamics with LLM Agents
arXiv:2604.04468v1 Announce Type: new Abstract: Evaluating retail strategies before deployment is difficult, as outcomes are determined across multiple stages,
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Scalable and Explainable Learner-Video Interaction Prediction using Multimodal Large Language Models
arXiv:2604.04482v1 Announce Type: new Abstract: Learners' use of video controls in educational videos provides implicit signals of cognitive processing and inst
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
Memory Intelligence Agent
arXiv:2604.04503v1 Announce Type: new Abstract: Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 4h ago
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
arXiv:2604.04514v1 Announce Type: new Abstract: AI coding agents operate in a paradox: they possess vast parametric knowledge yet cannot remember a conversation
Read paper → + Playlist