{"total":29,"rows":[{"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":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43,"area":"lr"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"area":"lr"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24,"area":"lr"},{"id":"2510.02837","title":"Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents","created":"2025-10-03","cited_by_count":24,"area":"lr"},{"id":"2501.18533","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","created":"2025-01-30","cited_by_count":21,"area":"lr"},{"id":"2410.11459","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","created":"2024-10-15","cited_by_count":19,"area":"lr"},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2501.17749","title":"Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation","created":"2025-01-29","cited_by_count":13,"area":"lr"},{"id":"2601.02346","title":"Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling","created":"2026-01-05","cited_by_count":13,"area":"lr"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2505.17244","title":"ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models","created":"2025-05-22","cited_by_count":9,"area":"lr"},{"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":"2509.14760","title":"Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2511.15169","title":"SafeRBench: Dissecting the Reasoning Safety of Large Language Models","created":"2025-11-19","cited_by_count":4,"area":"lr"},{"id":"2601.03537","title":"STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2406.06863","title":"Ollabench: Evaluating LLMs' Reasoning for Human-centric Interdependent Cybersecurity","created":"2024-06-11","cited_by_count":2,"area":"lr"},{"id":"2602.13562","title":"Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","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":"2606.08234","title":"SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2501.13952","title":"The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?","created":"2025-01-20","cited_by_count":0,"area":"lr"},{"id":"2602.05946","title":"f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment","created":"2026-02-05","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"}],"next_cursor":null}