Papers

New on arXiv

Fri 7 Nov 2025

244 papers

Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
Primal-Only Actor Critic Algorithm for Robust Constrained Average Cost MDPsDeep reinforcement learning methods → RL theory and sample complexity
CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and OptimizationLLM reasoning → Prompting and chain-of-thought reasoning
Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse AutoencoderMixture-of-experts → MoE large language models +1
OckBench: Measuring the Efficiency of LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
AdvisingWise: Supporting Academic Advising in Higher Education Settings Through a Human-in-the-Loop Multi-Agent FrameworkLLM agents and tool use → Educational agents and math problem solving
Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at ScaleLLM reasoning → Multimodal reasoning
Distributionally Robust Self Paced Curriculum Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Culture in Action: Evaluating Text-to-Image Models through Social ActivitiesDiffusion models → Image generation, text-to-image and editing
VLM-driven Skill Selection for Robotic Assembly TasksMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
KLASS: KL-Guided Fast Inference in Masked Diffusion ModelsDiffusion models → Discrete and text diffusion
Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge RobotsVision-language-action models → Generalist VLA models and benchmarks
BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait PredictionMixture-of-experts → Medical and biomedical MoE
TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement LearningLLM reasoning → Multimodal reasoning +1
On Flow Matching KL DivergenceDiffusion models → Flow matching, time series and science
A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?Knowledge distillation → Knowledge distillation for LLMs
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language ModelsLLM agents and tool use → Software engineering coding agents
APP: Accelerated Path Patching with Task-Specific PruningMechanistic interpretability → Circuits and mechanistic analysis
Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
Large Language Models for Explainable Threat IntelligenceRetrieval-augmented generation → Privacy and security of RAG
EveryDayVLA: A Vision-Language-Action Model for Affordable Robotic ManipulationVision-language-action models → Generalist VLA models and benchmarks
Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online InteractionDeep reinforcement learning methods → RL theory and sample complexity
PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality AssessmentLLM reasoning → Multimodal reasoning +1
TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation FrameworkLLM reasoning → Knowledge- and tool-augmented reasoning +3
ConVerse: Benchmarking Contextual Safety in Agent-to-Agent ConversationsLLM agents and tool use → Agent threats, guardrails and governance
Diffusion-Based Electromagnetic Inverse Design of Scattering Structured MediaDiffusion models → Flow matching, time series and science
Cleaning Maintenance Logs with LLM Agents for Improved Predictive MaintenanceLLM agents and tool use → General LLM agent frameworks and benchmarks
When More Retrieval Hurts: Retrieval-Augmented Code Review GenerationRetrieval-augmented generation → RAG for code
Building Specialized Software-Assistant ChatBot with Graph-Based Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
Embedding-Space Data Augmentation to Prevent Membership Inference Attacks in Clinical Time Series ForecastingLLM safety and security → Membership inference attacks
TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining
DeepEyesV2: Toward Agentic Multimodal ModelLLM agents and tool use → Multimodal and embodied agents
TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
Integrating Score-Based Diffusion Models with Machine Learning-Enhanced Localization for Advanced Data Assimilation in Geological Carbon StorageDiffusion models → Flow matching, time series and science
An End-to-End Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with DronesDeep reinforcement learning methods → RL for games and combinatorial optimization
FreeControl: Efficient, Training-Free Structural Control via One-Step Attention ExtractionDiffusion models → Image generation, text-to-image and editing
SIL: Symbiotic Interactive Learning for Language-Conditioned Human-Agent Co-AdaptationLLM agents and tool use → Multimodal and embodied agents
Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
Associative Poisoning to Generative Machine LearningLLM safety and security → Backdoor and data poisoning attacks
MUSE: Multi-Scale Dense Self-Distillation for Nucleus Detection and ClassificationKnowledge distillation → Distillation for medical imaging
Follow-Me in Micro-Mobility with End-to-End Imitation LearningOffline RL and imitation learning from data → Imitation and offline RL for driving
Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold StartDeep reinforcement learning methods → RL with diffusion and flow models
Agentic Link Construction for Environment and Intent Aware 6G CommunicationLLM agents and tool use → Agentic AI for wireless networks
Role-SynthCLIP: A Role Play Driven Diverse Synthetic Data ApproachSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual EmbeddingsLLM reasoning → Hallucination detection and mitigation +1
MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure RecoveryDiffusion models → Diffusion and flow policies for robotics
Multi-agent Coordination via Flow MatchingDiffusion models → Diffusion and flow policies for robotics
Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein BindingDiffusion models → Flow matching, time series and science
iFlyBot-VLM Technical ReportMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk PropertyRetrieval-augmented generation → Agentic RAG, agents and memory +1
DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement LearningLLM safety and security → Watermarking generated content and models
A benchmark multimodal oro-dental dataset for large vision-language modelsMultimodal LLMs / vision-language models → Medical vision-language models
Leak@k: Unlearning Does Not Make LLMs Forget Under Probabilistic DecodingLLM safety and security → Machine unlearning
AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval AgentLLM agents and tool use → Web, search, and research agents
You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base ModelsLLM reasoning → Reinforcement learning for reasoning
Real-Time Reasoning Agents in Evolving EnvironmentsLLM reasoning → Reasoning for agents, planning and code +1
Self-Interest and Systemic Benefits: Emergence of Collective Rationality in Mixed Autonomy Traffic Through Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
Beyond Clicking:A Step Towards Generalist GUI Grounding via Text Dragging
From Augmentation to Symbiosis: A Review of Human-AI Collaboration Frameworks, Performance, and Perils
Towards Trustworthy LLM-Based Recommendation via Rationale Integration
Cooperation Through Indirect Reciprocity in Child-Robot Interactions
Toward Better Generalization in Few-Shot Learning through the Meta-Component Combination
Predicting Grain Growth in Polycrystalline Materials Using Deep Learning Time Series Models
Global Feature Enhancing and Fusion Framework for Strain Gauge Time Series Classification
Mixture-of-Schedulers: An Adaptive Scheduling Agent as a Learned Router for Expert Policies
SA-EMO: Structure-Aligned Encoder Mixture of Operators for Generalizable Full-waveform Inversion
Omics-scale polymer computational database transferable to real-world artificial intelligence applications
MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks
Characterizing and Understanding Energy Footprint and Efficiency of Small Language Model on Edges
Evaluating LLM Understanding via Structured Tabular Decision Simulations
An Efficient and Almost Optimal Solver for the Joint Routing-Assignment Problem via Partial JRA and Large-α Optimization
Multi-period Learning for Financial Time Series Forecasting
The LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications
Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM
Motif 2 12.7B technical report
Dynamic Stability of LLM-Generated Code
It Takes Two: A Dual Stage Approach for Terminology-Aware Translation
Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution
An Efficient Gradient-Aware Error-Bounded Lossy Compressor for Federated Learning
Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being
Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs
A Second-Order Attention Mechanism For Prostate Cancer Segmentation and Detection in Bi-Parametric MRI
Language Generation: Complexity Barriers and Implications for Learning
Zero-Shot Function Encoder-Based Differentiable Predictive Control
Multi-Scale Feature Fusion and Graph Neural Network Integration for Text Classification with Large Language Models
In-Context Learning Without Copying
Near-Exponential Savings for Mean Estimation with Active Learning
Towards Better Ultrasound Video Segmentation Foundation Model: An Empirical study on SAM2 Finetuning from Data Perspective
QiVC-Net: Quantum-Inspired Variational Convolutional Network, with Application to Biosignal Classification
Compressing Chemistry Reveals Functional Groups
GastroDL-Fusion: A Dual-Modal Deep Learning Framework Integrating Protein-Ligand Complexes and Gene Sequences for Gastrointestinal Disease Drug Discovery
Persian Musical Instruments Classification Using Polyphonic Data Augmentation
Distributionally Robust Multimodal Machine Learning
TabDistill: Distilling Transformers into Neural Nets for Few-Shot Tabular Classification
Pedicle Screw Pairing and Registration for Screw Pose Estimation from Dual C-arm Images Using CAD Models
AI-assisted workflow enables rapid, high-fidelity breast cancer clinical trial eligibility prescreening
A Representation Sharpening Framework for Zero Shot Dense Retrieval
VMDT: Decoding the Trustworthiness of Video Foundation Models
Optimizing Diversity and Quality through Base-Aligned Model Collaboration
Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games

All 244