{"total":28,"rows":[{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2410.15686","title":"NetSafe: Exploring the Topological Safety of Multi-agent Networks","created":"2024-10-21","cited_by_count":29,"area":"agents"},{"id":"2505.17716","title":"Get Experience from Practice: LLM Agents with Record & Replay","created":"2025-05-23","cited_by_count":23,"area":"agents"},{"id":"2410.07672","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","created":"2024-10-10","cited_by_count":22,"area":"agents"},{"id":"2506.05739","title":"To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt","created":"2025-06-06","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2512.16310","title":"Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation","created":"2025-12-18","cited_by_count":11,"area":"agents"},{"id":"2510.17017","title":"SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents","created":"2025-10-19","cited_by_count":9,"area":"agents"},{"id":"2505.18397","title":"An Outlook on the Opportunities and Challenges of Multi-Agent AI Systems","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2507.06323","title":"Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms","created":"2025-07-08","cited_by_count":7,"area":"agents"},{"id":"2608.24777","title":"StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing","created":"2026-08-25","cited_by_count":6,"area":"agents"},{"id":"2505.22503","title":"Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation","created":"2025-05-28","cited_by_count":4,"area":"agents"},{"id":"2504.03185","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents","created":"2025-04-04","cited_by_count":2,"area":"agents"},{"id":"2511.03138","title":"DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents","created":"2025-11-05","cited_by_count":2,"area":"agents"},{"id":"2604.08551","title":"Self-Sovereign Agent","created":"2026-03-04","cited_by_count":2,"area":"agents"},{"id":"2508.15526","title":"SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking","created":"2025-08-21","cited_by_count":1,"area":"agents"},{"id":"2512.23717","title":"HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate","created":"2025-12-09","cited_by_count":1,"area":"agents"},{"id":"2601.19174","title":"SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks","created":"2026-01-27","cited_by_count":1,"area":"agents"},{"id":"2602.22697","title":"Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue","created":"2026-02-26","cited_by_count":1,"area":"agents"},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2607.02121","title":"Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring","created":"2026-07-02","cited_by_count":1,"area":"agents"},{"id":"2605.30838","title":"COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.25836","title":"AI Snitches Get Glitches: Towards Evading Agentic Surveillance","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.05462","title":"BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2609.15134","title":"HazardAuditor: From Executable Threats to Safer Computer-Use Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.34463","title":"CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.15150","title":"Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}