Papers

New on arXiv

Thu 1 Jan 2026

158 papers

Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World RoboticsDeep reinforcement learning methods → Deep RL algorithms and representations
Entropic Context Shaping: Information-Theoretic Filtering for Context-Aware LLM AgentsLLM agents and tool use → Agent memory systems
Deep Q-Network Based Resilient Drone Communication:Neutralizing First-Order Markov JammersDeep reinforcement learning methods → RL for robot navigation and UAV control
α3-Bench: A Unified Benchmark of Safety, Robustness, and Efficiency for LLM-Based UAV Agents over 6G NetworksLLM agents and tool use → Multimodal and embodied agents
Context Collapse: In-Context Learning and Model CollapseSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
MODE: Efficient Time Series Prediction with Mamba Enhanced by Low-Rank Neural ODEsState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
When Small Models Are Right for Wrong Reasons: Process Verification for Trustworthy AgentsLLM reasoning → Prompting and chain-of-thought reasoning +1
Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool FeedbackRetrieval-augmented generation → RAG for code
CPPO: Contrastive Perception Policy Optimization for VLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
Multi-Agent Coordinated Rename RefactoringLLM agents and tool use → Software engineering coding agents
MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and ObservabilityLLM agents and tool use → Software engineering coding agents
Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHubLLM agents and tool use → Software engineering coding agents
Progressive Ideation using an Agentic AI Framework for Human-AI Co-CreationLLM agents and tool use → General LLM agent frameworks and benchmarks
Geometric Regularization in Mixture-of-Experts: The Disconnect Between Weights and ActivationsMixture-of-experts → MoE theory and gating functions
Defensive M2S: Training Guardrail Models on Compressed Multi-turn ConversationsLLM safety and security → Jailbreaking
Imitation from Observations with Trajectory-Level Generative EmbeddingsOffline RL and imitation learning from data → Imitation learning methods
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow ModelsLLM reasoning → Reinforcement learning for reasoning +2
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular VideosWorld models → Video-generation world models and simulators
Vision-Language Reasoning for Geolocalization: A Reinforcement Learning ApproachLLM reasoning → Spatial and embodied reasoning +1
Bio-inspired Agentic Self-healing Framework for Resilient Distributed Computing Continuum SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection SeparationState-space sequence models (S4, Mamba) → Mamba for image restoration
Offline Multi-Agent Reinforcement Learning for 6G Communications: Fundamentals, Applications and Future DirectionsOffline RL and imitation learning from data → Offline multi-agent RL
Can Optimal Transport Improve Federated Inverse Reinforcement Learning?Offline RL and imitation learning from data → Inverse reinforcement learning +1
Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG SystemsRetrieval-augmented generation → Privacy and security of RAG
FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question AnsweringMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API ComplexityLLM agents and tool use → Tool learning and function calling
ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation RedirectionDiffusion models → Robustness, privacy and adversarial aspects
S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent SystemsRetrieval-augmented generation → Privacy and security of RAG +1
When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered AgentsLLM agents and tool use → Social simulation and multi-agent debate
Mitigating Latent Mismatch in cVAE-Based Singing Voice Synthesis via Flow MatchingDiffusion models → Audio, speech and music
From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain BenchmarkRetrieval-augmented generation → Medical and biomedical RAG
Disentangling Perception and Reasoning in Multimodal LLMs via Reward DesignLLM reasoning → Multimodal reasoning +1
Overlooked Safety Vulnerability in LLMs: Malicious Intelligent Optimization Algorithm Request and its JailbreakLLM safety and security → Jailbreaking
Towards a Benchmark for Dependency Decision-MakingLLM agents and tool use → Software engineering coding agents
Knowledge Distillation for Temporal Knowledge Graph Reasoning with Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
Reinforcement-Learned Unequal Error Protection for Quantized Semantic EmbeddingsDeep reinforcement learning methods → RL training of language and agent models
Online Finetuning Decision Transformers with Pure RL GradientsOffline RL and imitation learning from data → Decision transformers and sequence modeling
Reinforcement Learning with Function Approximation for Non-Markov ProcessesDeep reinforcement learning methods → RL theory and sample complexity
An AI Monkey Gets Grapes for Sure -- Sphere Neural Networks for Reliable Decision-MakingLLM reasoning → Reasoning benchmarks and evaluation
Traffic Simulation in Ad Hoc Network of Flying UAVs with Generative AI Adaptation
Simulation-Based Study of AI-Assisted Channel Adaptation in UAV-Enabled Cellular Networks
Bit-politeia: An AI Agent Community in Blockchain
Overview of the SciHigh Track at FIRE 2025: Research Highlight Generation from Scientific Papers
Enhancing the QA Model through a Multi-domain Debiasing Framework
The Hessian of tall-skinny networks is easy to invert
MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
Application of deep learning techniques in non-contrast computed tomography pulmonary angiogram for pulmonary embolism diagnosis
Complexity-based code embeddings
MetaFormer-driven Encoding Network for Robust Medical Semantic Segmentation
Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease
Attention Needs to Focus: A Unified Perspective on Attention Allocation
Four-Stage Alzheimer's Disease Classification from MRI Using Topological Feature Extraction, Feature Selection, and Ensemble Learning
Latent-Constrained Conditional VAEs for Augmenting Large-Scale Climate Ensembles
Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting
The Discovery Gap: How Product Hunt Startups Vanish in LLM Organic Discovery Queries
Device-Native Autonomous Agents for Privacy-Preserving Negotiations
Security Hardening Using FABRIC: Implementing a Unified Compliance Aggregator for Linux Servers
Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Study
A Chain-of-Thought Approach to Semantic Query Categorization in e-Commerce Taxonomies
Rule-Based Approaches to Atomic Sentence Extraction
MotionPhysics: Learnable Motion Distillation for Text-Guided Simulation
Interpretable Machine Learning for Quantum-Informed Property Predictions in Artificial Sensing Materials
Noise-Aware Named Entity Recognition for Historical VET Documents
Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning
Laplacian Kernelized Bandit
Combining Residual U-Net and Data Augmentation for Dense Temporal Segmentation of Spike Wave Discharges in Single-Channel EEG
Deep Networks Learn Deep Hierarchical Models
Controllable Concept Bottleneck Models
Language as Mathematical Structure: Examining Semantic Field Theory Against Language Games
A Comparative Study of Adaptation Strategies for Time Series Foundation Models in Anomaly Detection
Comparative Efficiency Analysis of Lightweight Transformer Models: A Multi-Domain Empirical Benchmark for Enterprise NLP Deployment
Toward Better Temporal Structures for Geopolitical Events Forecasting
Interpretable ML Under the Microscope: Performance, Meta-Features, and the Regression-Classification Predictability Gap
RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
Robust Assembly Progress Estimation via Deep Metric Learning
Can Semantic Methods Enhance Team Sports Tactics? A Methodology for Football with Broader Applications
Secure, Verifiable, and Scalable Multi-Client Data Sharing via Consensus-Based Privacy-Preserving Data Distribution
Deep Delta Learning
ABFR-KAN: Kolmogorov-Arnold Networks for Functional Brain Analysis
Do LLMs Judge Distantly Supervised Named Entity Labels Well? Constructing the JudgeWEL Dataset
Adaptive Causal Coordination Detection for Social Media: A Memory-Guided Framework with Semi-Supervised Learning
RoLID-11K: A Dashcam Dataset for Small-Object Roadside Litter Detection
Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving
Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models
NOS-Gate: Queue-Aware Streaming IDS for Consumer Gateways under Timing-Controlled Evasion
Engineering Attack Vectors and Detecting Anomalies in Additive Manufacturing
Word Frequency Counting Based on Serverless MapReduce
Sparse Tucker Decomposition and Graph Regularization for High-Dimensional Time Series Forecasting
In Line with Context: Repository-Level Code Generation via Context Inlining
BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognition
Mask-Conditioned Voxel Diffusion for Joint Geometry and Color Inpainting
PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devices
BERT-JEPA: Reorganizing CLS Embeddings for Language-Invariant Semantics
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
Deterministic Coreset for Lp Subspace
Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems
Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers
The Impact of Lesion Focus on the Performance of AI-Based Melanoma Classification
OmniVaT: Single Domain Generalization for Multimodal Visual-Tactile Learning

All 158