Papers

New on arXiv

Fri 28 Nov 2025

308 papers

ChunkNorris: A High-Performance and Low-Energy Approach to PDF Parsing and ChunkingRetrieval-augmented generation → Multimodal RAG
Autonomous QA Agent: A Retrieval-Augmented Framework for Reliable Selenium Script GenerationRetrieval-augmented generation → RAG pipeline design and evaluation +1
Distillation-based Scenario-Adaptive Mixture-of-Experts for the Matching Stage of Multi-scenario RecommendationMixture-of-experts → MoE for recommender systems
Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-TuningLLM agents and tool use → General LLM agent frameworks and benchmarks
A Modular LLM-Agent System for Transparent Multi-Parameter Weather InterpretationLLM agents and tool use → Financial trading and forecasting agents
Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability DetectionRetrieval-augmented generation → Privacy and security of RAG
LegalWebAgent: Empowering Access to Justice via LLM-Based Web AgentsLLM agents and tool use → Social simulation and multi-agent debate
Alleviating Choice Supportive Bias in LLM with Reasoning Dependency GenerationLLM reasoning → Reasoning benchmarks and evaluation
Watermarks for Embeddings-as-a-Service Large Language ModelsLLM safety and security → Watermarking generated content and models
Risk-Entropic Flow MatchingDiffusion models → Flow matching, time series and science
A Hierarchical Hybrid AI Approach: Integrating Deep Reinforcement Learning and Scripted Agents in Combat SimulationsDeep reinforcement learning methods → RL for games and combinatorial optimization
Optimizing Information Asset Investment Strategies in the Exploratory Phase of the Oil and Gas Industry: A Reinforcement Learning ApproachDeep reinforcement learning methods → Adversarial robustness and RL in finance
Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?LLM reasoning → Prompting and chain-of-thought reasoning
Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution SimulationLLM reasoning → Reasoning for agents, planning and code
Towards Corpus-Grounded Agentic LLMs for Multilingual Grammatical AnalysisLLM agents and tool use → General LLM agent frameworks and benchmarks
ReactionMamba: Generating Short & Long Human Reaction SequencesState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular ClassificationLLM reasoning → Reasoning for agents, planning and code
Generating Verifiable Chain of Thoughts from Exection-TracesLLM reasoning → Reasoning for agents, planning and code
RadDiff: Retrieval-Augmented Denoising Diffusion for Protein Inverse FoldingRetrieval-augmented generation → Medical and biomedical RAG +1
Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language ModelsLLM reasoning → Multimodal reasoning +1
Video-CoM: Interactive Video Reasoning via Chain of ManipulationsLLM reasoning → Multimodal reasoning +1
Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn InteractionWorld models → World models for language agents +1
Visual Generation TuningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated EnvironmentsWorld models → Latent predictive world models
ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory RolloutsOffline RL and imitation learning from data → Offline RL algorithms +1
Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgentDiffusion models → Discrete and text diffusion +3
Hunyuan-GameCraft-2: Instruction-following Interactive Game World ModelWorld models → Video-generation world models and simulators
MegaChat: A Synthetic Persian Q&A Dataset for High-Quality Sales Chatbot EvaluationRetrieval-augmented generation → Agentic RAG, agents and memory
FedSGT: Exact Federated Unlearning via Sequential Group-based TrainingLLM safety and security → Federated unlearning and poisoning
Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast ReportingLLM agents and tool use → Financial trading and forecasting agents
DEAL-300K: Diffusion-based Editing Area Localization with a 300K-Scale Dataset and Frequency-Prompted BaselineDiffusion models → Image generation, text-to-image and editing
Optimizing Multimodal Language Models through Attention-based InterpretabilityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery ApproachMechanistic interpretability → Knowledge and representations inside LLMs
Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model ApproachMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Multi-Modal Scene Graph with Kolmogorov-Arnold Experts for Audio-Visual Question AnsweringMixture-of-experts → Multimodal MoE models
MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report)LLM agents and tool use → Web, search, and research agents
Auditable Context-Aware HFMD Forecasting with Structured LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
OctoMed: Data Recipes for State-of-the-Art Multimodal Medical ReasoningLLM reasoning → Clinical and biomedical applications
Adapting Like Humans: A Metacognitive Agent with Test-time ReasoningLLM reasoning → Test-time compute and efficient thinking +2
AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for AgricultureLLM reasoning → Clinical and biomedical applications +1
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation EngineeringLLM reasoning → Reasoning benchmarks and evaluation +2
Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested EmbeddingsKnowledge distillation → Distillation for medical imaging
Obstruction reasoning for robotic graspingLLM reasoning → Spatial and embodied reasoning
Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad PredictionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Are LLMs Good Safety Agents or a Propaganda Engine?LLM safety and security → Safety alignment, refusal and guardrails
PowerCLIP: Powerset Alignment for Contrastive Pre-TrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
InstanceV: Instance-Level Video GenerationDiffusion models → Video generation
Multi-chain Graph Refinement and Selection for Reliable Reasoning in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video GenerationDiffusion models → Video generation
db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence ParallelismDiffusion models → Video generation
MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?LLM reasoning → Multimodal reasoning +1
NumeriKontrol: Adding Numeric Control to Diffusion Transformers for Instruction-based Image EditingDiffusion models → Image generation, text-to-image and editing
Does Self-Evaluation Enable Wireheading in Language Models?LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
Conveying Imagistic Thinking in Traditional Chinese Medicine Translation: A Prompt Engineering and LLM-Based Evaluation FrameworkLLM reasoning → Clinical and biomedical applications
MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
GOATex: Geometry & Occlusion-Aware TexturingDiffusion models → 3D, point cloud and scene generation
LatBot: Distilling Universal Latent Actions for Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining
From Illusion to Intention: Visual Rationale Learning for Vision-Language ReasoningLLM reasoning → Multimodal reasoning
Masked Diffusion for Generative RecommendationDiffusion models → Diffusion recommenders
JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
TIM-PRM: Verifying multimodal reasoning with Tool-Integrated PRMLLM reasoning → Multimodal reasoning +1
Guiding Visual Autoregressive Models through Spectrum WeakeningDiffusion models → Image generation, text-to-image and editing
McSc: Motion-Corrective Preference Alignment for Video Generation with Self-Critic Hierarchical ReasoningLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
BIFE: Better Interaction, Fewer Errors for Minute-Long Video GenerationWorld models → Video-generation world models and simulators +1
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact MatchEfficient LLM inference and serving → Speculative decoding
HMR3D: Hierarchical Multimodal Representation for 3D Scene Understanding with Large Vision-Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Visual Puns from Idioms: An Iterative LLM-T2IM-MLLM FrameworkMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
One-to-All Animation: Alignment-Free Character Animation and Image Pose TransferDiffusion models → Video generation
Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel ShufflingLLM safety and security → Watermarking generated content and models
Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion SymbolsMultimodal LLMs / vision-language models → Multimodal emotion understanding
Seeing before Observable: Potential Risk Reasoning in Autonomous Driving via Vision Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Language-conditioned world model improves policy generalization by reading environmental descriptionsWorld models → World models for language agents
Leveraging Textual Compositional Reasoning for Robust Change CaptioningLLM reasoning → Multimodal reasoning
From Points to Clouds: Learning Robust Semantic Distributions for Multi-modal PromptsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
ORION: Teaching Language Models to Reason Efficiently in the Language of ThoughtLLM reasoning → Test-time compute and efficient thinking
Adversarial Training for Process Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data AgentsLLM agents and tool use → Web, search, and research agents
Serving Heterogeneous LoRA Adapters in Distributed LLM Inference SystemsEfficient LLM inference and serving → Serving systems and request scheduling
Scalable Diffusion Transformer for Conditional 4D fMRI SynthesisDiffusion models → Medical imaging and segmentation
SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal NormsRetrieval-augmented generation → Legal and financial RAG
CRAwDAD: Causal Reasoning Augmentation with Dual-Agent DebateLLM reasoning → Causal reasoning in LLMs +1
Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document UnderstandingLLM agents and tool use → Multimodal and embodied agents
PerfMamba: Performance Analysis and Pruning of Selective State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Chained Prompting for Better Systematic Review Search Strategies
STELLAR: Structure-guided LLM Assertion Retrieval and Generation for Formal Verification
Finetuning Large Language Models for Automated Depression Screening in Nigerian Pidgin English: GENSCORE Pilot Study
Proceedings of the 20th International Conference on Knowledge, Information and Creativity Support Systems (KICSS 2025)
Efficient Asynchronous Federated Evaluation with Strategy Similarity Awareness for Intent-Based Networking in Industrial Internet of Things
Learning to Prioritize IT Tickets: A Comparative Evaluation of Embedding-based Approaches and Fine-Tuned Transformer Models
Context-Aware Detection and Victim-Centered Response Generation for Online Harassment in Private Messaging
Writing in Symbiosis: Mapping Human Creative Agency in the AI Era
IoTEdu: Access Control, Detection, and Automatic Incident Response in Academic IoT Networks
Banach neural operator for Navier-Stokes equations
ORCA: Open-ended Response Correctness Assessment for Audio Question Answering
Multivariate time series prediction using clustered echo state network

All 308