{"total":78,"rows":[{"id":"2503.18666","title":"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","created":"2025-03-24","cited_by_count":223,"area":"agents"},{"id":"2410.06703","title":"ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents","created":"2024-10-09","cited_by_count":133,"area":"agents"},{"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":"2510.09781","title":"Building a Foundational Guardrail for General Agentic Systems via Synthetic Data","created":"2025-10-10","cited_by_count":29,"area":"agents"},{"id":"2504.11168","title":"Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems","created":"2025-04-15","cited_by_count":26,"area":"safety"},{"id":"2504.14772","title":"Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions","created":"2025-04-20","cited_by_count":26,"area":"distill"},{"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":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2412.12004","title":"The Open Source Advantage in Large Language Models (LLMs)","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2602.06443","title":"TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents","created":"2026-02-06","cited_by_count":15,"area":"agents"},{"id":"2503.01742","title":"Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models","created":"2025-03-03","cited_by_count":11,"area":"safety"},{"id":"2508.19277","title":"POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization","created":"2025-08-23","cited_by_count":11,"area":"lr"},{"id":"2510.01270","title":"Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2508.05855","title":"Safety of Embodied Navigation: A Survey","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2506.23111","title":"FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2507.04105","title":"Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing","created":"2025-07-05","cited_by_count":9,"area":"agents"},{"id":"2502.20426","title":"Among Them: A game-based framework for assessing persuasion capabilities of LLMs","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2501.18626","title":"The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs","created":"2025-01-27","cited_by_count":7,"area":"safety"},{"id":"2502.19320","title":"Shh, don't say that! Domain Certification in LLMs","created":"2025-02-26","cited_by_count":7,"area":null},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7,"area":"agents"},{"id":"2510.14008","title":"Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment","created":"2025-10-15","cited_by_count":7,"area":"agents"},{"id":"2604.05229","title":"From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI","created":"2026-04-06","cited_by_count":7,"area":"agents"},{"id":"2502.18528","title":"ARACNE: An LLM-Based Autonomous Shell Pentesting Agent","created":"2025-02-24","cited_by_count":5,"area":"agents"},{"id":"2511.22047","title":"Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks","created":"2025-11-27","cited_by_count":5,"area":"safety"},{"id":"2603.15800","title":"Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory","created":"2026-03-16","cited_by_count":5,"area":"lr"},{"id":"2601.17003","title":"Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2411.12946","title":"A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection","created":"2024-11-20","cited_by_count":3,"area":"safety"},{"id":"2505.12287","title":"The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models","created":"2025-05-18","cited_by_count":3,"area":"safety"},{"id":"2510.05310","title":"RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts","created":"2025-10-06","cited_by_count":3,"area":"safety"},{"id":"2601.03181","title":"Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2605.17169","title":"Responsible Agentic AI Requires Explicit Provenance","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2502.11006","title":"Prompt Inject Detection with Generative Explanation as an Investigative Tool","created":"2025-02-16","cited_by_count":2,"area":"safety"},{"id":"2504.14212","title":"Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification","created":"2025-04-19","cited_by_count":2,"area":null},{"id":"2507.20503","title":"Customize Multi-modal RAI Guardrails with Precedent-based predictions","created":"2025-07-28","cited_by_count":2,"area":"safety"},{"id":"2509.16861","title":"AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software","created":"2025-09-21","cited_by_count":2,"area":"safety"},{"id":"2510.12993","title":"Tailored untruths: How personalisation challenges LLM safeguards","created":"2025-10-14","cited_by_count":2,"area":"safety"},{"id":"2511.16884","title":"Generative AI in Sociological Research: State of the Discipline","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2602.07954","title":"Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation","created":"2026-02-08","cited_by_count":2,"area":null},{"id":"2604.15579","title":"Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents","created":"2026-04-16","cited_by_count":2,"area":"safety"},{"id":"2604.18775","title":"An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models","created":"2026-04-20","cited_by_count":2,"area":"safety"},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2502.01472","title":"FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model","created":"2025-02-03","cited_by_count":1,"area":"alignment"},{"id":"2508.19093","title":"Retrieval-Augmented Generation for Natural Language Art Provenance Searches in the Getty Provenance Index","created":"2025-08-26","cited_by_count":1,"area":"rag"},{"id":"2509.16870","title":"DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems","created":"2025-09-21","cited_by_count":1,"area":"safety"},{"id":"2510.14207","title":"Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks","created":"2025-10-16","cited_by_count":1,"area":"agents"},{"id":"2601.00994","title":"ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social Systems","created":"2026-01-02","cited_by_count":1,"area":"agents"},{"id":"2601.22269","title":"JAF: Judge Agent Forest","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","created":"2026-02-01","cited_by_count":1,"area":"diffusion"},{"id":"2602.15689","title":"A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"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":"2605.03255","title":"Do LLMs have core beliefs?","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2606.29887","title":"SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing","created":"2026-06-29","cited_by_count":1,"area":"safety"},{"id":"2406.11880","title":"Knowledge Return Oriented Prompting (KROP)","created":"2024-06-11","cited_by_count":0,"area":"safety"},{"id":"2410.22151","title":"Standardization Trends on Safety and Trustworthiness Technology for Advanced AI","created":"2024-10-29","cited_by_count":0,"area":"lr"},{"id":"2411.16730","title":"\"Moralized\" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks","created":"2024-11-23","cited_by_count":0,"area":"safety"},{"id":"2506.05368","title":"Speaking images. A novel framework for the automated self-description of artworks","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2511.04215","title":"Black-Box Guardrail Reverse-engineering Attack","created":"2025-11-06","cited_by_count":0,"area":"safety"},{"id":"2512.13821","title":"The Double Life of Code World Models: Provably Unmasking Malicious Behavior Through Execution Traces","created":"2025-12-15","cited_by_count":0,"area":"wm"},{"id":"2512.15081","title":"Quantifying Return on Security Controls in LLM Systems","created":"2025-12-17","cited_by_count":0,"area":"safety"},{"id":"2602.19215","title":"Understanding Empirical Unlearning with Combinatorial Interpretability","created":"2026-02-22","cited_by_count":0,"area":"safety"},{"id":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2603.25097","title":"ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents","created":"2026-03-26","cited_by_count":0,"area":"agents"},{"id":"2604.16314","title":"Software Self-Extension with SelfEvolve: an Agentic Architecture for Runtime Code Generation","created":"2026-02-06","cited_by_count":0,"area":"agents"},{"id":"2604.27464","title":"Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study","created":"2026-04-30","cited_by_count":0,"area":"agents"},{"id":"2605.23448","title":"AI Security Research Should Better Incentivize Defense Research","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.20258","title":"Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.13078","title":"Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.09510","title":"Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.15673","title":"PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2608.19579","title":"Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics","created":"2026-08-20","cited_by_count":0,"area":"safety"},{"id":"2608.20378","title":"Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2609.00519","title":"The Safeguard Worked. Is the LLM System Safer?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.15533","title":"The Misery of Mechanistic Interpretability: A Formal Perspective","created":"2026-09-14","cited_by_count":0,"area":"mechinterp"},{"id":"2609.22712","title":"Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2610.10742","title":"BRANCH: Bypassing Multi-Scanner AI Guardrails","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.16312","title":"Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.18007","title":"Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}