{"total":33,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2312.11970","title":"Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives","created":"2023-12-19","cited_by_count":257,"area":"agents"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2402.05863","title":"How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis","created":"2024-02-08","cited_by_count":100,"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":"2407.15325","title":"Odyssey: Empowering Minecraft Agents with Open-World Skills","created":"2024-07-22","cited_by_count":26,"area":"agents"},{"id":"2512.09321","title":"ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data","created":"2025-12-10","cited_by_count":18,"area":"agents"},{"id":"2506.02064","title":"The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims","created":"2025-06-01","cited_by_count":14,"area":"agents"},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2506.10764","title":"OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems","created":"2025-06-12","cited_by_count":12,"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":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2603.11337","title":"RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents","created":"2026-03-11","cited_by_count":10,"area":"agents"},{"id":"2508.08501","title":"GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games","created":"2025-08-11","cited_by_count":9,"area":"agents"},{"id":"2310.20499","title":"Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models","created":"2023-10-31","cited_by_count":8,"area":"agents"},{"id":"2601.14230","title":"MASCOT: Multi-Agent Socio-Collaborative Companion Systems","created":"2026-01-20","cited_by_count":7,"area":"agents"},{"id":"2404.09339","title":"Towards Practical Tool Usage for Continually Learning LLMs","created":"2024-04-14","cited_by_count":6,"area":"agents"},{"id":"2509.16494","title":"Can an Individual Manipulate the Collective Decisions of Multi-Agents?","created":"2025-09-20","cited_by_count":5,"area":"agents"},{"id":"2410.15701","title":"When LLMs Learn to be Students: The SOEI Framework for Modeling and Evaluating Virtual Student Agents in Educational Interaction","created":"2024-10-21","cited_by_count":4,"area":"agents"},{"id":"2501.19339","title":"PixelWorld: How Far Are We from Perceiving Everything as Pixels?","created":"2025-01-31","cited_by_count":4,"area":"agents"},{"id":"2505.04628","title":"How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks","created":"2025-04-04","cited_by_count":4,"area":"agents"},{"id":"2506.00739","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","created":"2025-05-31","cited_by_count":4,"area":"agents"},{"id":"2510.07309","title":"Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"id":"2505.10670","title":"Interpretable Risk Mitigation in LLM Agent Systems","created":"2025-05-15","cited_by_count":3,"area":"agents"},{"id":"2605.11269","title":"gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2510.01295","title":"The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation","created":"2025-10-01","cited_by_count":2,"area":"agents"},{"id":"2510.06872","title":"Prototyping Multimodal GenAI Real-Time Agents with Counterfactual Replays and Hybrid Wizard-of-Oz","created":"2025-10-08","cited_by_count":2,"area":"agents"},{"id":"2310.09773","title":"RSVP: Customer Intent Detection via Agent Response Contrastive and Generative Pre-Training","created":"2023-10-15","cited_by_count":1,"area":"agents"},{"id":"2509.07389","title":"Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLM agents","created":"2025-09-09","cited_by_count":1,"area":"agents"},{"id":"2512.13481","title":"neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings","created":"2025-12-15","cited_by_count":1,"area":"agents"},{"id":"2604.12177","title":"Policy-Invisible Violations in LLM-Based Agents","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2605.25701","title":"Neural Router: Semantic Content Matching for Agentic AI","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2606.25195","title":"SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward","created":"2026-06-23","cited_by_count":0,"area":"agents"}],"next_cursor":null}