{"total":15,"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":"2410.12855","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","created":"2024-10-11","cited_by_count":47,"area":"agents"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2509.14284","title":"The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration","created":"2025-09-16","cited_by_count":20,"area":"agents"},{"id":"2405.20770","title":"Large Language Model Sentinel: LLM Agent for Adversarial Purification","created":"2024-05-24","cited_by_count":10,"area":"agents"},{"id":"2601.04034","title":"HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense","created":"2026-01-07","cited_by_count":8,"area":"agents"},{"id":"2602.11749","title":"AIR: Improving Agent Safety through Incident Response","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2605.11882","title":"On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment","created":"2026-05-12","cited_by_count":8,"area":"agents"},{"id":"2603.03371","title":"Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs","created":"2026-03-02","cited_by_count":3,"area":"agents"},{"id":"2505.15738","title":"Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses","created":"2025-05-21","cited_by_count":2,"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":"2508.06963","title":"MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair","created":"2025-08-09","cited_by_count":0,"area":"agents"},{"id":"2508.14323","title":"Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever","created":"2025-08-20","cited_by_count":0,"area":"agents"},{"id":"2604.09056","title":"Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout","created":"2026-04-10","cited_by_count":0,"area":"agents"},{"id":"2608.00134","title":"Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks","created":"2026-07-31","cited_by_count":0,"area":"agents"}],"next_cursor":null}