{"total":20,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367,"area":"agents"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2310.05418","title":"Humanoid Agents: Platform for Simulating Human-like Generative Agents","created":"2023-10-09","cited_by_count":73,"area":"agents"},{"id":"2304.13835","title":"Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models","created":"2023-04-26","cited_by_count":54,"area":"agents"},{"id":"2407.01093","title":"IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation","created":"2024-07-01","cited_by_count":35,"area":"agents"},{"id":"2401.05033","title":"Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk","created":"2024-01-10","cited_by_count":34,"area":"agents"},{"id":"2406.08689","title":"Security of AI Agents","created":"2024-06-12","cited_by_count":26,"area":"agents"},{"id":"2312.17653","title":"LARP: Language-Agent Role Play for Open-World Games","created":"2023-12-24","cited_by_count":24,"area":"agents"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2512.03318","title":"Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia","created":"2025-12-03","cited_by_count":12,"area":"agents"},{"id":"2407.05305","title":"MINDECHO: Role-Playing Language Agents for Key Opinion Leaders","created":"2024-07-07","cited_by_count":10,"area":"agents"},{"id":"2307.15833","title":"Dialogue Shaping: Empowering Agents through NPC Interaction","created":"2023-07-28","cited_by_count":8,"area":"agents"},{"id":"2402.08392","title":"Large Language Models as Minecraft Agents","created":"2024-02-13","cited_by_count":7,"area":"agents"},{"id":"2412.13549","title":"EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents","created":"2024-12-18","cited_by_count":6,"area":"agents"},{"id":"2502.20807","title":"Digital Player: Evaluating Large Language Models based Human-like Agent in Games","created":"2025-02-28","cited_by_count":6,"area":"agents"},{"id":"2407.12734","title":"A LLM Benchmark based on the Minecraft Builder Dialog Agent Task","created":"2024-07-17","cited_by_count":4,"area":"agents"},{"id":"2408.11574","title":"Drama Engine: A Framework for Narrative Agents","created":"2024-08-21","cited_by_count":3,"area":"agents"},{"id":"2605.08503","title":"NARRA-Gym for Evaluating Interactive Narrative Agents","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2608.11236","title":"TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation","created":"2026-07-31","cited_by_count":1,"area":"agents"}],"next_cursor":null}