{"total":18,"rows":[{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2505.14590","title":"MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol","created":"2025-05-20","cited_by_count":34,"area":null},{"id":"2501.08579","title":"LLM-based Human Simulations Have Not Yet Been Reliable","created":"2025-01-15","cited_by_count":30,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2405.19946","title":"Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf","created":"2024-05-30","cited_by_count":24,"area":null},{"id":"2409.20222","title":"Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2505.11336","title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","created":"2025-05-16","cited_by_count":7,"area":null},{"id":"2506.12421","title":"Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints","created":"2025-06-14","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2510.11618","title":"StoryBox: Collaborative Multi-Agent Simulation for Hybrid Bottom-Up Long-Form Story Generation Using Large Language Models","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2403.02757","title":"In-Memory Learning: A Declarative Learning Framework for Large Language Models","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2506.21784","title":"MobiVerse: Scaling Urban Mobility Simulation with Hybrid Lightweight Domain-Specific Generator and Large Language Models","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2605.07462","title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.25815","title":"Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.14778","title":"FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaboration","created":"2026-06-10","cited_by_count":1,"area":null}],"next_cursor":null}