Papers

New on arXiv

Thu 7 Aug 2025

395 papers

ARL-Based Multi-Action Market Making with Hawkes Processes and Variable VolatilityDeep reinforcement learning methods → Adversarial robustness and RL in finance
FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question AnsweringLLM agents and tool use → Financial trading and forecasting agents
A Survey on Video Temporal Grounding with Multimodal Large Language ModelMultimodal LLMs / vision-language models → Video understanding with MLLMs
RTTC: Reward-Guided Collaborative Test-Time ComputeLLM reasoning → Test-time compute and efficient thinking +2
FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge DistillationKnowledge distillation → General knowledge distillation methods
HiSTM: Hierarchical Spatiotemporal Mamba for Cellular Traffic ForecastingState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Quantum-Efficient Reinforcement Learning Solutions for Last-Mile On-Demand DeliveryDeep reinforcement learning methods → Quantum reinforcement learning
HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI ReconstructionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly DetectionLLM reasoning → Chain-of-thought reasoning for driving
IRL-VLA: Training an Vision-Language-Action Policy via Reward World ModelWorld models → Embodied and robot world models +2
Operationalizing Serendipity: Multi-Agent AI Workflows for Enhanced Materials Characterization with Theory-in-the-LoopLLM agents and tool use → Medical and scientific domain agents
ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding UpdatesMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Large language models show fragile cognitive reasoning about human emotionsLLM reasoning → Audio-language model reasoning
A Markov Decision Process Framework for Early Maneuver Decisions in Satellite Collision AvoidanceDeep reinforcement learning methods → RL for robot navigation and UAV control
Interpretable Modeling of Driver Attention Shifts with a Vision-Language ModelMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Integrating Vision Foundation Models with Reinforcement Learning for Enhanced Object InteractionDeep reinforcement learning methods → RL for robot locomotion and manipulation
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLMLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive LossDiffusion models → Medical imaging and segmentation
UnGuide: Learning to Forget with LoRA-Guided Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
WebWatcher: Breaking New Frontier of Vision-Language Deep Research AgentLLM agents and tool use → Multimodal and embodied agents
InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy OptimizationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
CLAPP: The CLASS LLM Agent for Pair ProgrammingLLM agents and tool use → Web, search, and research agents
Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid ControlLLM agents and tool use → Financial trading and forecasting agents
Genie Envisioner: A Unified World Foundation Platform for Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty HandlingDeep reinforcement learning methods → RL for robot navigation and UAV control
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward RectificationLLM reasoning → Reinforcement learning for reasoning
How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn ConversationsMechanistic interpretability → Probing deception, bias and beliefs
Simulating Human-Like Learning Dynamics with LLM-Empowered AgentsLLM agents and tool use → Educational agents and math problem solving
The Missing Reward: Active Inference in the Era of ExperienceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Learning to Reason for FactualityLLM reasoning → Hallucination detection and mitigation
Test-Time Reinforcement Learning for GUI Grounding via Region ConsistencyLLM reasoning → Multimodal reasoning +1
GroundAct: Can LLM Agents Ground Actions in Environmental States?LLM agents and tool use → General LLM agent frameworks and benchmarks
Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning +1
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic ShuffleLLM reasoning → Multimodal reasoning +1
Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and VisionLLM reasoning → Multimodal reasoning
LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced PolicyLLM reasoning → Mathematical reasoning
Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data SynthesisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social MediaLLM safety and security → Safety alignment, refusal and guardrails
Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Adapting Vision-Language Models Without Labels: A Comprehensive SurveyMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
AI vs. Human Moderators: A Comparative Evaluation of Multimodal LLMs in Content Moderation for Brand SafetyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM FeedbackRetrieval-augmented generation → Generation and context integration
Auto-Eval Judge: Towards a General Agentic Framework for Task Completion EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video ClipsDiffusion models → Diffusion and flow policies for robotics
AutoIAD: Manager-Driven Multi-Agent Collaboration for Automated Industrial Anomaly DetectionLLM agents and tool use → Software engineering coding agents
MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning CapabilitiesLLM reasoning → Test-time compute and efficient thinking +1
MM2CT: MR-to-CT translation for multi-modal image fusion with mambaState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly DetectionDiffusion models → Flow matching, time series and science
Multimodal LLM-assisted Evolutionary Search for Programmatic Control PoliciesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf InteractionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
LLM-based Multi-Agent Copilot for Quantum SensorLLM agents and tool use → Medical and scientific domain agents
From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based NeutralizationLLM safety and security → Backdoor and data poisoning attacks
DeepPHY: Benchmarking Agentic VLMs on Physical ReasoningLLM reasoning → Spatial and embodied reasoning +2
DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning ModelEnd-to-end autonomous driving → End-to-end system architecture
UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Real-Time Iteration Scheme for Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward ModelsLLM reasoning → Multimodal reasoning +2
Can Language Models Critique Themselves? Investigating Self-Feedback for Retrieval Augmented Generation at BioASQ 2025Retrieval-augmented generation → Agentic RAG, agents and memory +1
Information-Theoretic Graph Fusion with Vision-Language-Action Model for Policy Reasoning and Dual Robotic ControlLLM reasoning → Spatial and embodied reasoning +1
The Term 'Agent' Has Been Diluted Beyond Utility and Requires RedefinitionLLM agents and tool use → General LLM agent frameworks and benchmarks
Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection SuppressionLLM reasoning → Test-time compute and efficient thinking
Textual Inversion for Efficient Adaptation of Open-Vocabulary Object Detectors Without ForgettingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQAMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
A Novel Architecture for Symbolic Reasoning with Decision Trees and LLM AgentsLLM reasoning → Reasoning benchmarks and evaluation +1
ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
Estimating Musical Surprisal from Audio in Autoregressive Diffusion Model Noise SpacesDiffusion models → Audio, speech and music
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in TokensLLM reasoning → Diffusion reasoning and test-time scaling
Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and InteractionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational RecommendersLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
SGDFuse: SAM-Guided Diffusion Model for High-Fidelity Infrared and Visible Image FusionDiffusion models → Image generation, text-to-image and editing
MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMsMixture-of-experts → MoE large language models
Navigating the Trade-off: A Synthesis of Defensive Strategies for Zero-Shot Adversarial Robustness in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
ArbiViewGen: Controllable Arbitrary Viewpoint Camera Data Generation for Autonomous Driving via Stable Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and DistillationLLM reasoning → Audio-language model reasoning
ReasoningTrack: Chain-of-Thought Reasoning for Long-term Vision-Language TrackingLLM reasoning → Multimodal reasoning
VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided OptimizationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing ImagesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
QA-Dragon: Query-Aware Dynamic RAG System for Knowledge-Intensive Visual Question AnsweringMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
STEPWISE-CODEX-Bench: Evaluating Complex Multi-Function Comprehension and Fine-Grained Execution ReasoningLLM reasoning → Reasoning for agents, planning and code
Learning to See and Act: Task-Aware Virtual View Exploration for Robotic ManipulationVision-language-action models → 3D and spatial-aware VLA
ReCode: Reinforcing Code Generation with Reasoning-Process RewardsLLM reasoning → Reinforcement learning for reasoning +1
PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving SystemsLLM reasoning → Chain-of-thought reasoning for driving +2
Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Domain-driven Metrics for Reinforcement Learning: A Case Study on Epidemic Control using Agent-based SimulationDeep reinforcement learning methods → RL for clinical treatment and surgery
PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics AlignmentLLM reasoning → Clinical and biomedical applications
Navigating Through Paper Flood: Advancing LLM-based Paper Evaluation through Domain-Aware Retrieval and Latent ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
Reasoning through Exploration: A Reinforcement Learning Framework for Robust Function CallingLLM reasoning → Reinforcement learning for reasoning +1
Beyond Automation: Socratic AI, Epistemic Agency, and the Implications of the Emergence of Orchestrated Multi-Agent Learning ArchitecturesLLM agents and tool use → Educational agents and math problem solving
RAP: Real-time Audio-driven Portrait Animation with Video Diffusion TransformerDiffusion models → Audio, speech and music
BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual SteeringMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
MedMKEB: A Comprehensive Knowledge Editing Benchmark for Medical Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
Cognitive Duality for Adaptive Web AgentsLLM agents and tool use → Web, search, and research agents

All 395