{"total":20,"rows":[{"id":"2504.15257","title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","created":"2025-04-21","cited_by_count":63,"area":null},{"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":"2602.23636","title":"FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation","created":"2026-02-27","cited_by_count":7,"area":null},{"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":"2602.01618","title":"SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia","created":"2026-02-02","cited_by_count":2,"area":null},{"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":"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":"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":"2606.09165","title":"Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges","created":"2026-06-08","cited_by_count":0,"area":null},{"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":"2608.29098","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}],"next_cursor":null}