Sign In

Daily Arxiv

New
전 세계에서 발간되는 인공지능 관련 논문을 정리하는 페이지 입니다. 본 페이지는 Google Gemini를 활용해 요약 정리하며, 비영리로 운영 됩니다. 논문에 대한 저작권은 저자 및 해당 기관에 있으며, 요약본 공유 시 출처만 명기하면 됩니다. This service is supported by Google Gemini.
LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents
Audio LLMs Know When They Can't Hear You
T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation
HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases
Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworks
Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content
Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study
Benchy: towards a universal language for task-oriented AI benchmarks
BioEVAL: A global, multi-institutional benchmark of large language and multimodal models for bioengineering
Do LLMs Understand Context? A Knowledge Graph-Based Evaluation Framework
Pretrained ASR Pseudo-labeling for Noisy Police Audio
Spectral Feedback for Test-Time Alignment of Protein Diffusion Models
Predicting Transmembrane Protein Topology from 3D Structure
A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol
When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess
ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?
Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence
Training Object Permanence in World Models
Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment
DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs
BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
Pistis Technical Report
PAWS: Policy-driven Agentic World Simulation
TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split
When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
Reinforcement Learning with Decomposed Subtasks
Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts
Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution
Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment
Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations
TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse
4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting
Do Existing Preconditioners Improve Biomedical Tabular Foundation Learning? An Empirical Study on TabPFN Optimization
Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation
DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement
Offline Multimodal Large Language Models for Decision Support in Air Operations
LEGIT: Credentialing Protocol for Trustworthy AI Agent Marketplaces
GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development
Efficient Benchmarking in Production: A Study of an Evolving LLM Agent
PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking
CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition
A Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning
Ability-Residual Decoupled Modeling for Affective Cognitive Diagnosis
Information-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation
AI-GRACE: A Use-Case Operationalization Framework for Agentic AI: From Organizational Objectives and Obligations to Deployment Capabilities and Architecture
Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks
SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity
Can Agents Design Better Chips with a Higher Level Abstraction?
Clinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake
TinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers
Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models
Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing
LoRA Enhanced Contrastive Learning with SAS Vision Transformers
CaLR: Causal Latent Revision for Robust Diffusion Reasoning
Attention-Aware Routing: Coupling Routing and Attention in MoEs
RBS-Attention: Radius-Bounded Sparse Prefill for Long-Context Large Language Models
Do AI Agents Understand Computer Architecture?
Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses
What Do Current Systematic Generalization Tasks Miss? A Reasoning-Centered Analysis
Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer
What Do We Expect from LLMs? Mapping the Design of LLM Benchmarks
BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research
Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes
SNOMED CT Concept Recommendation from Masked Clinical Context
Learning Heterogeneous Preferences
A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning
FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment
SAGE: Governed Artifact Generation from Enterprise Guidelines
Imitation Learning for Autonomous Driving in CARLA
A Systematic Evaluation of the COTQ Provincial Land Cover Product: Structural Consistency, Spectral Separability, and Relative Positioning Against ESA, ESRI, and Google Products
NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation
GVD: Governed Versioning and Deduplication for Document Repositories
GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph Agents
CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video
What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization
Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
One Color Preprocessing Improves DSATUR
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records
Calibrate, Then Route: A Measured Study of Learned Request Routing for Disaggregated LLM Serving
Position: AI Is Not Ready for Strategic Conflicts
GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events
Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation
Optimal Pruning for Neural Architectures using Fisher Information Distances
How User-AI Mistreatment Occurs and Matters in Conversational Systems?
Causal multi-modal AI for personalized chemosensitivity prediction
Planning or Learning: Reliability and Cost in Multi-Asset Maintenance
A Hybrid Agentic AI Framework for Intelligent Supply Chain Analytics
Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems
Toward a Decision-Assurance Layer for AI-Assisted Flight Planning in Air Traffic Management
AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents
Asclepius: An Adaptive Harness for Long-Horizon Clinical Agents
From Legal Text to AI-specific Risk Sources: A Systematic Analysis of the EU AI Act's High-Risk Requirements
Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation
Token Efficient Task Execution via Application Behavior Modeling for Web Agents
New
Made with Slashpage