Papers

New on arXiv

Fri 16 Jan 2026

290 papers

VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating AgentsLLM agents and tool use → Medical and scientific domain agents
AutoBinder Agent: An MCP-Based Agent for End-to-End Protein Binder DesignLLM agents and tool use → Medical and scientific domain agents
Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer ManifoldsLLM reasoning → Prompting and chain-of-thought reasoning
The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News DetectionLLM reasoning → Multimodal reasoning +1
Shortest-Path Flow Matching with Mixture-Conditioned Bases for OOD Generalization to Unseen ConditionsDiffusion models → Flow matching, time series and science
AI Co-Scientist for Knowledge Synthesis in Medical Contexts: A Proof of ConceptRetrieval-augmented generation → Medical and biomedical RAG
POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office AutomationLLM agents and tool use → Agent threats, guardrails and governance
RobotDesignGPT: Automated Robot Design Synthesis using Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generationSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
Risk-Aware Human-in-the-Loop Framework with Adaptive Intrusion Response for Autonomous VehiclesEnd-to-end autonomous driving → Reinforcement learning for driving +1
Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language ModelsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation ModelsLLM reasoning → Spatial and embodied reasoning
RAC: Retrieval-Augmented Clarification for Faithful Conversational SearchRetrieval-augmented generation → Conversational and speech RAG
jBOT: Semantic Jet Representation Clustering Emerges from Self-DistillationKnowledge distillation → General knowledge distillation methods
Semantic Caching and Intent-Driven Context Optimization for Multi-Agent Natural Language to Code SystemsLLM agents and tool use → Web, search, and research agents
From Everything-is-a-File to Files-Are-All-You-Need: How Unix Philosophy Informs the Design of Agentic AI SystemsLLM agents and tool use → Software engineering coding agents
MATEX: Multi-scale Attention and Text-guided Explainability of Medical Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +2
Do explanations generalize across large reasoning models?LLM reasoning → Reasoning benchmarks and evaluation
Building Production-Ready Probes For GeminiLLM safety and security → Prompt injection and agent security
Generative Scenario Rollouts for End-to-End Autonomous DrivingVision-language-action models → VLA for autonomous driving +1
Low-Rank Key Value AttentionEfficient LLM inference and serving → KV cache optimization
MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
When Are Two Scores Better Than One? Investigating Ensembles of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Predict the Retrieval! Test time adaptation for Retrieval Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive MapsLLM reasoning → Spatial and embodied reasoning
The unreasonable effectiveness of pattern matchingLLM reasoning → Reasoning benchmarks and evaluation
The Great March 100: 100 Detail-oriented Tasks for Evaluating Embodied AI AgentsOffline RL and imitation learning from data → Robot manipulation imitation learning
New Adaptive Mechanism for Large Neighborhood Search using Dual Actor-CriticDeep reinforcement learning methods → RL for games and combinatorial optimization
ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +2
Evaluating LLM Behavior in Hiring: Implicit Weights, Fairness Across Groups, and Alignment with Human PreferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Reward Modeling for Scientific Writing EvaluationLLM reasoning → Knowledge- and tool-augmented reasoning +1
Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance GraphsLLM agents and tool use → Financial trading and forecasting agents
Think-Clip-Sample: Slow-Fast Frame Selection for Video UnderstandingLLM reasoning → Multimodal reasoning +1
AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning ProblemsLLM reasoning → Reasoning for agents, planning and code +1
Offline Reinforcement-Learning-Based Power Control for Application-Agnostic Energy EfficiencyOffline RL and imitation learning from data → Decision transformers and sequence modeling
How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response DraftingLLM alignment / RLHF / preference optimisation → Medical LLM alignment
Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language ModelsRetrieval-augmented generation → Generation and context integration +1
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
Can Small Agents Collaborate to Beat a Single Large Language Model?LLM agents and tool use → General LLM agent frameworks and benchmarks
Enhancing Vision Language Models with Logic Reasoning for Situational AwarenessLLM reasoning → Multimodal reasoning +1
Membership Inference on LLMs in the WildLLM safety and security → Membership inference attacks
Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning +1
FTDMamba: Frequency-Assisted Temporal Dilation Mamba for Unmanned Aerial Vehicle Video Anomaly DetectionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
Beyond Model Scaling: Test-Time Intervention for Efficient Deep ReasoningLLM reasoning → Test-time compute and efficient thinking
VLAgents: A Policy Server for Efficient VLA InferenceVision-language-action models → Efficient VLA inference and adaptation
Language of Thought Shapes Output Diversity in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Model-free policy gradient for discrete-time mean-field controlDeep reinforcement learning methods → RL for games and combinatorial optimization
T^star: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement LearningDiffusion models → Discrete and text diffusion
VidLeaks: Membership Inference Attacks Against Text-to-Video ModelsLLM safety and security → Membership inference attacks
LoRA as OracleLLM safety and security → Backdoor and data poisoning attacks
SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG +1
ATATA: One Algorithm to Align Them AllDiffusion models → Flow matching, time series and science
Policy-Based Deep Reinforcement Learning Hyperheuristics for Job-Shop Scheduling ProblemsDeep reinforcement learning methods → RL for energy, networks and operations
Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent SystemsLLM reasoning → Reasoning for agents, planning and code +1
Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive IntegrationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal ReasoningLLM reasoning → Multimodal reasoning +2
ReCreate: Reasoning and Creating Domain Agents Driven by ExperienceLLM reasoning → Reasoning for agents, planning and code +1
Integrity Shield A System for Ethical AI Use & Authorship Transparency in AssessmentsLLM safety and security → Watermarking generated content and models
PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative ModelsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Generation of Chest CT pulmonary Nodule Images by Latent Diffusion Models using the LIDC-IDRI DatasetDiffusion models → Medical imaging and segmentation
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World DevelopmentLLM agents and tool use → Software engineering coding agents
EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot CollaborationLLM reasoning → Spatial and embodied reasoning
Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMsLLM reasoning → Reinforcement learning for reasoning
M3DDM+: An improved video outpainting by a modified masking strategyDiffusion models → 3D, point cloud and scene generation
CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World ContextsLLM agents and tool use → General LLM agent frameworks and benchmarks
Budget-Aware Anytime Reasoning with LLM-Synthesized Preference DataLLM reasoning → Test-time compute and efficient thinking
BAPO: Boundary-Aware Policy Optimization for Reliable Agentic SearchLLM agents and tool use → Web, search, and research agents
Self-Augmented Mixture-of-Experts for QoS PredictionMixture-of-experts → MoE theory and gating functions
PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMsMechanistic interpretability → SAE features and their applications
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-PlayingLLM agents and tool use → Social simulation and multi-agent debate
NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG SystemsRetrieval-augmented generation → RAG robustness and adaptive retrieval
Reasoning Distillation for Lightweight Automated Program RepairLLM reasoning → Reasoning for agents, planning and code +1
ZPD Detector: Data Selection via Capability-Difficulty Alignment for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Toward Adaptive Grid Resilience: A Gradient-Free Meta-RL Framework for Critical Load RestorationDeep reinforcement learning methods → RL for energy, networks and operations
AJAR: Adaptive Jailbreak Architecture for Red-teamingLLM safety and security → Prompt injection and agent security
Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
SwiftKV: An Edge-Oriented Attention Algorithm and Multi-Head Accelerator for Fast, Efficient LLM DecodingEfficient LLM inference and serving → KV cache optimization
MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline ReinforcementLLM reasoning → Clinical and biomedical applications +1
PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient DiagnosisMultimodal LLMs / vision-language models → Medical vision-language models
Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAGRetrieval-augmented generation → Privacy and security of RAG +1
Data-Efficient Curation for Multimodal Reasoning under Fixed Training ProtocolsLLM reasoning → Multimodal reasoning
Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface imagesDiffusion models → Medical imaging and segmentation
Domain-Specific Query Understanding for Automotive Applications: A Modular and Scalable Approach
Retrieval-Augmented Large Language Models for Evidence-Informed Guidance on Cannabidiol Use in Older Adults
Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Tasks
Are we chasing ghosts? Quantifying unattributable polarization, and attributing the rest to annotator groups
Measurement for Opaque Systems: Multi-source Triangulation with Interpretable Machine Learning
Early Warning Signals Appear Long Before Dropping Out: An Idiographic Approach Grounded in Complex Dynamic Systems Theory
Beyond Static Question Banks: Dynamic Knowledge Expansion via LLM-Automated Graph Construction and Adaptive Generation
STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
Integrating Color Histogram Analysis and Convolutional Neural Network for Skin Lesion Classification
Emergent Specialization in Learner Populations: Competition as the Source of Diversity
Bench4HLS: End-to-End Evaluation of LLMs in High-Level Synthesis Code Generation
Continuous-Flow Data-Rate-Aware CNN Inference on FPGA
oculomix: Hierarchical Sampling for Retinal-Based Systemic Disease Prediction
DecHW: Heterogeneous Decentralized Federated Learning Exploiting Second-Order Information

All 290