Papers

New on arXiv

Sun 12 Apr 2026

243 papers

Reinforcement Learning-Guided NSGA-II Enhanced with Gray Relational Coefficient for Multi-Objective Optimization: Application to NASDAQ Portfolio OptimizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Modeling Community Attitude through Reaction Tone: A Human-AI Collaborative Framework for Evaluating LLM Alignment with Linguistic Behaviors in Online CommunitiesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Agent-Facing Information Design in LLM Tool RegistriesLLM agents and tool use → Financial trading and forecasting agents
LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge DeploymentMixture-of-experts → Efficient MoE training and inference systems
Designing a double deep reinforcement learning selection tool for resilient demand predictionDeep reinforcement learning methods → RL for energy, networks and operations
Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Latent-Compressed Variational Autoencoder for Video Diffusion ModelsDiffusion models → Diffusion foundations and sampling
UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image GeneratorsLLM safety and security → Watermarking generated content and models
Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation SimulationLLM agents and tool use → Social simulation and multi-agent debate
Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical ReasoningLLM reasoning → Clinical and biomedical applications
Query Lower Bounds for Diffusion SamplingDiffusion models → Diffusion foundations and sampling
BridgeSim: Unveiling the OL-CL Gap in End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
Resilient Write: A Six-Layer Durable Write Surface for LLM Coding AgentsLLM agents and tool use → Software engineering coding agents
HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow MatchingDiffusion models → Diffusion and flow policies for robotics
Know Thy Reasoner: Not All Language Models Explore AlikeLLM reasoning → Test-time compute and efficient thinking
PokeRL: Reinforcement Learning for Pokemon RedDeep reinforcement learning methods → RL for games and combinatorial optimization
Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code AnalysisLLM agents and tool use → Agent threats, guardrails and governance
TInR: Exploring Tool-Internalized Reasoning in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis TreatmentLLM alignment / RLHF / preference optimisation → Medical LLM alignment
HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
MMRareBench: A Rare-Disease Multimodal and Multi-Image Medical BenchmarkMultimodal LLMs / vision-language models → Medical vision-language models
How You Ask Matters! Adaptive RAG Robustness to Query VariationsRetrieval-augmented generation → RAG robustness and adaptive retrieval
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form GenerationLLM agents and tool use → Web, search, and research agents
RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg GameLLM agents and tool use → Agent threats, guardrails and governance
When More Thinking Hurts: Overthinking in LLM Test-Time Compute ScalingLLM reasoning → Test-time compute and efficient thinking
Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTSRetrieval-augmented generation → Agentic RAG, agents and memory
Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed RewardsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Detecting RAG Extraction Attack via Dual-Path Runtime Integrity GameRetrieval-augmented generation → Privacy and security of RAG +1
Backbone-Conditional Behavior of Modality Gating in Multi-Modal Prostate MRI Segmentation: A 5-Fold Cross-Validation and Gate Mechanism AnalysisState-space sequence models (S4, Mamba) → Mamba for medical image analysis
FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
Do LLMs Build Spatial World Models? Evidence from Grid-World Maze TasksWorld models → World models for language agents +1
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive WeightingLLM reasoning → Prompting and chain-of-thought reasoning +1
Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry AlignmentOffline RL and imitation learning from data → Robot manipulation imitation learning +1
HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object PlacementDiffusion models → Image generation, text-to-image and editing
Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Efficient Process Reward Modeling via Contrastive Mutual InformationLLM reasoning → Reinforcement learning for reasoning +1
Mitigating Privacy Risk via Forget Set-Free UnlearningLLM safety and security → Machine unlearning
On the Optimization Landscape of Observer-based Dynamic Linear Quadratic ControlDeep reinforcement learning methods → RL for games and combinatorial optimization
MoEITS: A Green AI approach for simplifying MoE-LLMsMixture-of-experts → MoE large language models
Rethinking Software Engineering for Agentic AI SystemsLLM reasoning → Reasoning for agents, planning and code +1
CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning TasksLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Afford CorrespondenceOffline RL and imitation learning from data → Robot manipulation imitation learning
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language ModelsDiffusion models → Discrete and text diffusion
Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?LLM agents and tool use → General LLM agent frameworks and benchmarks
WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series ForecastingMixture-of-experts → MoE for time series and graphs
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMsEfficient LLM inference and serving → KV cache optimization
BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum LearningLLM reasoning → Spatial and embodied reasoning +1
Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy EvaluationLLM reasoning → Reasoning benchmarks and evaluation
Beyond Compliance: A Resistance-Informed Motivation Reasoning Framework for Challenging Psychological Client SimulationLLM reasoning → Clinical and biomedical applications
A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal HallucinationsLLM reasoning → Hallucination detection and mitigation +1
CARO: Chain-of-Analogy Reasoning Optimization for Robust Content ModerationLLM reasoning → Reasoning benchmarks and evaluation +1
CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMsLLM reasoning → Reasoning benchmarks and evaluation
Visual Enhanced Depth Scaling for Multimodal Latent ReasoningLLM reasoning → Multimodal reasoning
CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-ExpertsMixture-of-experts → MoE large language models
SWE-Shepherd: Advancing PRMs for Reinforcing Code AgentsLLM agents and tool use → Software engineering coding agents
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMsLLM agents and tool use → Web, search, and research agents
PEMAND: Persona-Enriched Multi-Agent Negotiation for Household Decision-MakingLLM agents and tool use → Social simulation and multi-agent debate
From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal ConsultationLLM reasoning → Reasoning for agents, planning and code +1
Rethinking the Diffusion Model from a Langevin PerspectiveDiffusion models → Diffusion foundations and sampling
Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm DetectionLLM safety and security → Watermarking generated content and models
EviCare: Enhancing Diagnosis Prediction with Deep Model-Guided Evidence for In-Context ReasoningLLM reasoning → Clinical and biomedical applications
SignReasoner: Compositional Reasoning for Complex Traffic Sign Understanding via Functional Structure UnitsLLM reasoning → Chain-of-thought reasoning for driving
AnySlot: Goal-Conditioned Vision-Language-Action Policies for Zero-Shot Slot-Level PlacementVision-language-action models → 3D and spatial-aware VLA
Safety Guarantees in Zero-Shot Reinforcement Learning for Cascade Dynamical SystemsDeep reinforcement learning methods → Safe and constrained RL
A Queueing-Theoretic Framework for Dynamic Attack Surfaces: Data-Integrated Risk Analysis and Adaptive DefenseDeep reinforcement learning methods → Adversarial robustness and RL in finance
DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary DomainLLM reasoning → Multimodal reasoning +1
Membership Inference Attacks Expose Participation Privacy in ECG Foundation EncodersLLM safety and security → Membership inference attacks
CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG InterpretationLLM reasoning → Clinical and biomedical applications
Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMsLLM safety and security → Jailbreaking
BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error DetectionRetrieval-augmented generation → Medical and biomedical RAG +1
TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detectionLLM reasoning → Clinical and biomedical applications +1
Benchmarking Open-Weight Foundation Models for Global AI Technical Governance
RuleEdit: Failure-Guided Human-AI Model Editing with Prospective Impact Preview
Specialty-Specific Medical Language Model for Immune-Mediated Diseases
No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand
Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation
Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
Measuring Changes in Instructor Class Design and Student Learning After the Release of Large Language Models (LLMs)
Toward Measuring AI's Effects on Skill Formation: The Stock-Formation Gap
TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
Positioning radiata pine branches requiring pruning by drone stereo vision
Mapping High-Performance Regions in Battery Scheduling across Data Uncertainty, Battery Design, and Planning Horizons
AutoFlows++: Hierarchical Message Flow Mining for System on Chip Designs
The Code Whisperer: LLM and Graph-Based AI for Smell and Vulnerability Resolution
A Lightweight Global-Target Framework for Multi-Domain No-Reference Image Quality Assessment in UAV Imagery
DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions
Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents
A Layer-wise Analysis of Supervised Fine-Tuning
Training single-electron and single-photon stochastic physical neural networks
Uncertainty-Aware Sparse Identification of Dynamical Systems via Bayesian Model Averaging
A Benchmark for Gap and Overlap Analysis as a Test of KG Task Readiness

All 243