Papers

New on arXiv

Sat 17 Jan 2026

154 papers

ELLMPEG: An Edge-based Agentic LLM Video Processing ToolLLM agents and tool use → Multimodal and embodied agents
Representation Learning Enhanced Deep Reinforcement Learning for Optimal Operation of Hydrogen-based Multi-Energy SystemsDeep reinforcement learning methods → RL for energy, networks and operations
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream UtilityLLM reasoning → Multimodal reasoning
Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
Who Owns Creativity and Who Does the Work? Trade-offs in LLM-Supported Research IdeationLLM agents and tool use → Web, search, and research agents
Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI PackagesLLM agents and tool use → Agent threats, guardrails and governance
From LLMs to Agents in Programming: The Impact of Providing an LLM with a CompilerLLM agents and tool use → Software engineering coding agents
Listen, Look, Drive: Coupling Audio Instructions for User-aware VLA-based Autonomous DrivingVision-language-action models → VLA for autonomous driving +1
DriveSafe: A Hierarchical Risk Taxonomy for Safety-Critical LLM-Based Driving AssistantsEnd-to-end autonomous driving → Large language models for driving +1
EMoE: Eigenbasis-Guided Routing for Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
UniMo: Unified Motion Generation and Understanding with Chain of ThoughtLLM reasoning → Spatial and embodied reasoning
Offline Policy Learning with Weight Clipping and Heaviside Composite OptimizationOffline RL and imitation learning from data → Offline RL algorithms
BiKC+: Bimanual Hierarchical Imitation with Keypose-Conditioned Coordination-Aware Consistency PoliciesOffline RL and imitation learning from data → Robot manipulation imitation learning
Powerful Training-Free Membership Inference Against Autoregressive Language ModelsLLM safety and security → Membership inference attacks
Mitigating Cultural Bias in LLMs via Multi-Agent Cultural DebateLLM agents and tool use → Social simulation and multi-agent debate
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM PersonalizationRetrieval-augmented generation → RAG pipeline design and evaluation
To Copy or Not to Copy: Copying Is Easier to Induce Than RecallRetrieval-augmented generation → RAG robustness and adaptive retrieval
Learning Stochastic Bridges for Video Object Removal via Video-to-Video TranslationDiffusion models → Inverse problems and image restoration
A New Strategy for Artificial Intelligence: Training Foundation Models Directly on Human Brain DataDeep reinforcement learning methods → Deep RL algorithms and representations
Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Partial Reasoning in Language Models: Search and Refinement Guided by UncertaintyLLM reasoning → Test-time compute and efficient thinking
ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking AgentsLLM agents and tool use → Agent memory systems
Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from ReviewsLLM agents and tool use → Agentic recommender systems
Acting Flatterers via LLMs Sycophancy: Combating Clickbait with LLMs Opposing-Stance ReasoningLLM reasoning → Causal reasoning in LLMs
Extreme Value Policy Optimization for Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
Process In-Context Learning: Enhancing Mathematical Reasoning via Dynamic Demonstration InsertionLLM reasoning → Reasoning benchmarks and evaluation
One-Shot Price Forecasting with Covariate-Guided Experts under Privacy ConstraintsMixture-of-experts → MoE for time series and graphs
AVIR: Adaptive Visual In-Document Retrieval for Efficient Multi-Page Document Question AnsweringMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-ImprovementSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
R2PO: Decoupling Rollout and Inference Policies for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
PEARL: Self-Evolving Assistant for Time Management with Reinforcement LearningSynthetic data and self-improvement for LLMs → Self-evolving LLM agents +1
Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning ConfidenceLLM reasoning → Test-time compute and efficient thinking
Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe ExplorationDeep reinforcement learning methods → Safe and constrained RL
Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive RestartLLM reasoning → Test-time compute and efficient thinking
LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context UnderstandingLLM agents and tool use → Agent memory systems
A Training-Free Guess What Vision Language Model from Snippets to Open-Vocabulary Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM ReasoningLLM reasoning → Reasoning for agents, planning and code
AEMA: Verifiable Evaluation Framework for Trustworthy and Controlled Agentic LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control FrameworkLLM agents and tool use → Agent threats, guardrails and governance
Agentic-R: Learning to Retrieve for Agentic SearchLLM agents and tool use → Web, search, and research agents
TF-CoDiT: Conditional Time Series Synthesis with Diffusion Transformers for Treasury FuturesDiffusion models → Flow matching, time series and science
Advances in LLM Reasoning Enable Flexibility in Clinical Problem-SolvingLLM reasoning → Clinical and biomedical applications
CTPD: Cross Tokenizer Preference DistillationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
Utilizing Metadata for Better Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Imandra CodeLogician: Neuro-Symbolic Reasoning for Precise Analysis of Software LogicLLM reasoning → Reasoning benchmarks and evaluation
Wildfire Suppression: Complexity, Models, and Instances
An Overlay Multicast Routing Method Based on Network Situational Awareness and Hierarchical Multi-Agent Reinforcement Learning
Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?
Assessing LLM Reliability on Temporally Recent Open-Domain Questions
Automated Optimization Modeling via a Localizable Error-Driven Perspective
Nested Named Entity Recognition in Plasma Physics Research Articles
Reviewing the Reviewer: LLM-Assisted Reviewer Feedback Generation for Guideline Compliance
Strategies for Creating Uncertainty in the AI Era to Trigger Students Critical Thinking: Pedagogical Design, Assessment Rubric, and Exam System
PALMA: A Lightweight Tropical Algebra Library for ARM-Based Embedded Systems
Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
VeRVE: Versatile Retrieval for Videos via Unified Embeddings
Aletheia: What Makes RLVR For Code Verifiers Tick?
Tolerance Principle and Small Language Model Learning
Federated Learning for the Design of Parametric Insurance Indices under Heterogeneous Renewable Production Losses
The Language You Ask In: Language-Conditioned Ideological Divergence in LLM Analysis of Contested Political Documents
Streaming Operator Inference for Model Reduction of Large-Scale Dynamical Systems
Inverse Rendering for High-Genus 3D Surface Meshes from Multi-view Images with Persistent Homology Priors
Analyzing Cancer Patients' Experiences with Embedding-based Topic Modeling and LLMs
Enhanced Diagnostic Performance via Large-Resolution Inference Optimization for Pathology Foundation Models
Principal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks
Segment and Matte Anything in a Unified Model
Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling
TIDE: A Trace-Informed Depth-First Exploration for Planning with Temporally Extended Goals
Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learning
Bengali Text Classification: An Evaluation of Large Language Model Approaches
SolarGPT-QA: A Domain-Adaptive Large Language Model for Educational Question Answering in Space Weather and Heliophysics
SynQP: A Framework and Metrics for Evaluating the Quality and Privacy Risk of Synthetic Data
Lost in Aggregation: The Causal Interpretation of the IV Estimand
CARLA-Round: A Multi-Factor Simulation Dataset for Roundabout Trajectory Prediction
RCDN: Real-Centered Detection Network for Robust Face Forgery Identification
Energy-Aware Ensemble Learning for Coffee Leaf Disease Classification
Large language models struggle with ethnographic text annotation
Neural Isomorphic Fields: A Transformer-based Algebraic Numerical Embedding
PTL-PINNs: Perturbation-Guided Transfer Learning with Physics- Informed Neural Networks for Nonlinear Systems
Detecting 3D Line Segments for 6DoF Pose Estimation with Limited Data
Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models
Conditional Random Fields for Interactive Refinement of Histopathological Predictions
Toward Real-World High-Precision Image Matting and Segmentation
EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space
CroBIM-V: Memory-Quality Controlled Remote Sensing Referring Video Object Segmentation
Bridging the Gap in Bangla Healthcare: Machine Learning Based Disease Prediction Using a Symptoms-Disease Dataset
ARMARecon: An ARMA Convolutional Filter based Graph Neural Network for Neurodegenerative Dementias Classification
Learning Language-Driven Sequence-Level Modal-Invariant Representations for Video-Based Visible-Infrared Person Re-Identification
Codebook-Injected Dialogue Segmentation for Multi-Utterance Constructs Annotation: LLM-Assisted and Gold-Label-Free Evaluation
Automating Parameter Selection in Deep Image Prior for Fluorescence Microscopy Image Denoising via Similarity-Based Parameter Transfer
Task-Driven Prompt Learning: A Joint Framework for Multi-modal Cloud Removal and Segmentation
A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models
textitFocaLogic: Logic-Based Interpretation of Visual Model Decisions
Nonlinear Dynamic Factor Analysis With a Transformer Network
Subargument Argumentation Frameworks: Separating Direct Conflict from Structural Dependency
Multimodal Feedback for Handheld Tool Guidance: Combining Wrist-Based Haptics with Augmented Reality
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection

All 154