Daily Arxiv

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, 공유 시 출처만 명기하면 됩니다.

Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering

SciDER: Scientific Data-centric End-to-end Researcher

Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents

GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning

MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning

The Observer-Situation Lattice: A Unified Formal Basis for Perspective-Aware Cognition

HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts

Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation

ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context

Opponent State Inference Under Partial Observability: An HMM-POMDP Framework for 2026 Formula 1 Energy Strategy

Information-Theoretic Framework for Self-Adapting Model Predictive Controllers

Beyond Reward: A Bounded Measure of Agent Environment Coupling

Extended Empirical Validation of the Explainability Solution Space

The Lattice Representation Hypothesis of Large Language Models

A Unified Framework to Quantify Cultural Intelligence of AI

Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics

How Well Does Agent Development Reflect Real-World Work?

Incremental LTLf Synthesis

Semantic XPath: Structured Agentic Memory Access for Conversational AI

DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

FCN-LLM: Empower LLM for Brain Functional Connectivity Network Understanding via Graph-level Multi-task Instruction Tuning

HVR-Met: A Hypothesis-Verification-Replaning Agentic System for Extreme Weather Diagnosis

DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage

Alien Science: Sampling Coherent but Cognitively Unavailable Research Directions from Idea Atoms

MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning

CollabEval: Enhancing LLM-as-a-Judge via Multi-Agent Collaboration

Tracking Capabilities for Safer Agents

HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents

BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains

MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind

The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents

MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning

AIoT-based Continuous, Contextualized, and Explainable Driving Assessment for Older Adults

MemPO: Self-Memory Policy Optimization for Long-Horizon Agents

K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control

InfoPO: Information-Driven Policy Optimization for User-Centric Agents

LiTS: A Modular Framework for LLM Tree Search

TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces

Machine Learning Grade Prediction Using Students' Grades and Demographics

Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger

Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs

MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation

Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs

SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks

EMPA: Evaluating Persona-Aligned Empathy as a Process

Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation

LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks

DenoiseFlow: Uncertainty-Aware Denoising for Reliable LLM Agentic Workflows

AI Runtime Infrastructure

LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks

From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems

Why Not? Solver-Grounded Certificates for Explainable Mission Planning

Optimizing In-Context Demonstrations for LLM-based Automated Grading

MED-COPILOT: A Medical Assistant Powered by GraphRAG and Similar Patient Case Retrieval

Confusion-Aware Rubric Optimization for LLM-based Automated Grading

NeuroHex: Highly-Efficient Hex Coordinate System for Creating World Models to Enable Adaptive AI

Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning

Monotropic Artificial Intelligence: Toward a Cognitive Taxonomy of Domain-Specialized Language Models

EmCoop: A Framework and Benchmark for Embodied Cooperation Among LLM Agents

How Well Do Multimodal Models Reason on ECG Signals?

DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths

TraderBench: How Robust Are AI Agents in Adversarial Capital Markets?

Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking

AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech

ReDON: Recurrent Diffractive Optical Neural Processor with Reconfigurable Self-Modulated Nonlinearity

LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning

LFQA-HP-1M: A Large-Scale Human Preference Dataset for Long-Form Question Answering

KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning

Pseudo Contrastive Learning for Diagram Comprehension in Multimodal Models

Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning

SDMixer: Sparse Dual-Mixer for Time Series Forecasting

BRIDGE the Gap: Mitigating Bias Amplification in Automated Scoring of English Language Learners via Inter-group Data Augmentation

CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentation

Evidential Neural Radiance Fields

Flowette: Flow Matching with Graphette Priors for Graph Generation

Hierarchical Multi-Scale Graph Learning with Knowledge-Guided Attention for Whole-Slide Image Survival Analysis

Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents

Humans and LLMs Diverge on Probabilistic Inferences

Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision

SegReg: Latent Space Regularization for Improved Medical Image Segmentation

FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments

TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving

Optimization of Edge Directions and Weights for Mixed Guidance Graphs in Lifelong Multi-Agent Path Finding

BiKA: Kolmogorov-Arnold-Network-inspired Ultra Lightweight Neural Network Hardware Accelerator

SALIENT: Frequency-Aware Paired Diffusion for Controllable Long-Tail CT Detection

Human Supervision as an Information Bottleneck: A Unified Theory of Error Floors in Human-Guided Learning

DesignSense: A Human Preference Dataset and Reward Modeling Framework for Graphic Layout Generation

Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG

Long Range Frequency Tuning for QML

Learning to Generate Secure Code via Token-Level Rewards

Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages

Hello-Chat: Towards Realistic Social Audio Interactions

Now You See Me: Designing Responsible AI Dashboards for Early-Stage Health Innovation

Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG

Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA

Domain-Partitioned Hybrid RAG for Legal Reasoning: Toward Modular and Explainable Legal AI for India

Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents

Reason to Contrast: A Cascaded Multimodal Retrieval Framework

Made with Slashpage