{"total":100,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135,"area":"mllm"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2504.15257","title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","created":"2025-04-21","cited_by_count":63,"area":null},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2505.21936","title":"RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments","created":"2025-05-28","cited_by_count":46,"area":"agents"},{"id":"2506.02456","title":"VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents","created":"2025-06-03","cited_by_count":45,"area":"agents"},{"id":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"id":"2510.13220","title":"EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems","created":"2025-10-15","cited_by_count":37,"area":"agents"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2506.04245","title":"Contextual Integrity in LLMs via Reasoning and Reinforcement Learning","created":"2025-05-29","cited_by_count":31,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2509.02563","title":"DynaGuard: A Dynamic Guardian Model With User-Defined Policies","created":"2025-09-02","cited_by_count":19,"area":"safety"},{"id":"2504.20472","title":"Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction","created":"2025-04-29","cited_by_count":16,"area":"safety"},{"id":"2505.20087","title":"Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models","created":"2025-05-26","cited_by_count":16,"area":"lr"},{"id":"2504.08848","title":"X-Guard: Multilingual Guard Agent for Content Moderation","created":"2025-04-11","cited_by_count":13,"area":"agents"},{"id":"2509.24296","title":"DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models","created":"2025-09-29","cited_by_count":12,"area":"safety"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2505.19139","title":"The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2510.04398","title":"SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations","created":"2025-10-05","cited_by_count":9,"area":null},{"id":"2601.22964","title":"EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2505.14035","title":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2505.19690","title":"Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2507.21652","title":"UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases","created":"2025-07-29","cited_by_count":7,"area":"lr"},{"id":"2512.05485","title":"TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations","created":"2025-12-05","cited_by_count":7,"area":"safety"},{"id":"2601.03868","title":"What Matters For Safety Alignment?","created":"2026-01-07","cited_by_count":7,"area":"alignment"},{"id":"2602.23636","title":"FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation","created":"2026-02-27","cited_by_count":7,"area":null},{"id":"2604.17562","title":"SafeAgent: A Runtime Protection Architecture for Agentic Systems","created":"2026-04-19","cited_by_count":7,"area":"agents"},{"id":"2605.11514","title":"FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems","created":"2026-05-12","cited_by_count":7,"area":"agents"},{"id":"2505.12348","title":"Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification","created":"2025-05-18","cited_by_count":6,"area":"lr"},{"id":"2509.11629","title":"Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2606.22873","title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","created":"2026-06-22","cited_by_count":6,"area":"lr"},{"id":"2607.19829","title":"DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection","created":"2026-07-22","cited_by_count":6,"area":"safety"},{"id":"2504.08104","title":"Geneshift: Impact of different scenario shift on Jailbreaking LLM","created":"2025-04-10","cited_by_count":5,"area":"safety"},{"id":"2605.17329","title":"LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails","created":"2026-05-17","cited_by_count":5,"area":"lr"},{"id":"2507.12314","title":"Thought Purity: A Defense Framework For Chain-of-Thought Attack","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2508.04204","title":"ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments","created":"2025-08-06","cited_by_count":4,"area":"lr"},{"id":"2508.20151","title":"IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2512.18027","title":"CoPE: A Small Language Model for Steerable and Scalable Content Labeling","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2512.23573","title":"ProGuard: Towards Proactive Multimodal Safeguard","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2605.07982","title":"GLiGuard: Schema-Conditioned Classification for LLM Safeguard","created":"2026-05-08","cited_by_count":4,"area":"safety"},{"id":"2510.21049","title":"Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2601.08000","title":"Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety","created":"2026-01-12","cited_by_count":3,"area":"lr"},{"id":"2602.18193","title":"BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards","created":"2026-02-20","cited_by_count":3,"area":"lr"},{"id":"2605.14454","title":"LiSA: Lifelong Safety Adaptation via Conservative Policy Induction","created":"2026-05-14","cited_by_count":3,"area":"safety"},{"id":"2509.22250","title":"Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2602.01618","title":"SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.03328","title":"GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2602.21346","title":"Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment","created":"2026-02-24","cited_by_count":2,"area":"lr"},{"id":"2603.17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.16824","title":"SafeDream: Safety World Model for Proactive Early Jailbreak Detection","created":"2026-04-18","cited_by_count":2,"area":"wm"},{"id":"2605.28830","title":"Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2605.29427","title":"FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2503.10944","title":"Phishsense-1B: A Technical Perspective on an AI-Powered Phishing Detection Model","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2506.13464","title":"Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2508.03054","title":"Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning","created":"2025-08-05","cited_by_count":1,"area":"lr"},{"id":"2508.16406","title":"Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models","created":"2025-08-22","cited_by_count":1,"area":"rag"},{"id":"2509.25896","title":"LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models","created":"2025-09-30","cited_by_count":1,"area":"mllm"},{"id":"2511.12861","title":"From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models","created":"2025-11-17","cited_by_count":1,"area":"lr"},{"id":"2602.15853","title":"A Lightweight Explainable Guardrail for Prompt Safety","created":"2026-01-24","cited_by_count":1,"area":"safety"},{"id":"2604.07655","title":"Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.26872","title":"When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2605.29068","title":"Robust and Efficient Guardrails with Latent Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.31073","title":"ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2607.17575","title":"A Dual-Hypothesis Reasoning Framework for LLM Guardrails","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2607.21401","title":"When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2608.03201","title":"When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models","created":"2026-08-04","cited_by_count":1,"area":"safety"},{"id":"2609.21793","title":"CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation","created":"2026-09-18","cited_by_count":1,"area":"safety"},{"id":"2508.07139","title":"A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection","created":"2025-08-10","cited_by_count":0,"area":"alignment"},{"id":"2602.06630","title":"TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2604.01473","title":"SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits","created":"2026-04-01","cited_by_count":0,"area":"safety"},{"id":"2604.10502","title":"CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2604.10504","title":"CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2604.12308","title":"ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.25893","title":"$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.03601","title":"DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.09165","title":"Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.13737","title":"FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization","created":"2026-06-11","cited_by_count":0,"area":"safety"},{"id":"2607.06326","title":"DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2608.00180","title":"C-Instrument: Automating RL Data Generation and Hillclimbing with a Constitution-Grid Instrument","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.03838","title":"LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.15594","title":"TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2608.29098","title":"SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.13657","title":"Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.13734","title":"PolicyMem: Geometric Policy Memory for LLM Governance","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.21484","title":"HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.12813","title":"VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.14443","title":"Specification-Based Testing of Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"},{"id":"2610.17473","title":"REA: From Correct LLM Judgments to Safe Decision Delivery","created":"2026-10-12","cited_by_count":0,"area":"safety"},{"id":"2610.18304","title":"Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}