{"total":28,"rows":[{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548,"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":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125,"area":"agents"},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2402.14865","title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","created":"2024-02-21","cited_by_count":54,"area":"agents"},{"id":"2405.20267","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","created":"2024-05-30","cited_by_count":42,"area":"agents"},{"id":"2407.06423","title":"InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation","created":"2024-07-08","cited_by_count":32,"area":"agents"},{"id":"2402.17168","title":"Benchmarking Data Science Agents","created":"2024-02-27","cited_by_count":30,"area":"agents"},{"id":"2506.01055","title":"Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution","created":"2025-06-01","cited_by_count":26,"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":"2505.02847","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","created":"2025-05-01","cited_by_count":21,"area":"agents"},{"id":"2509.10397","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","created":"2025-09-12","cited_by_count":19,"area":"agents"},{"id":"2504.07046","title":"A Unified Agentic Framework for Evaluating Conditional Image Generation","created":"2025-04-09","cited_by_count":15,"area":"agents"},{"id":"2505.19477","title":"Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge","created":"2025-05-26","cited_by_count":11,"area":"agents"},{"id":"2605.19196","title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","created":"2026-05-18","cited_by_count":10,"area":"agents"},{"id":"2505.16086","title":"Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development","created":"2025-05-22","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":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2406.07054","title":"CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation","created":"2024-06-11","cited_by_count":2,"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":"2604.06452","title":"Learning to Interrupt in Language-based Multi-agent Communication","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2606.22329","title":"BabelJudge: Measuring LLM-as-a-Judge Reliability Across Languages and Agent Trajectories","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2607.12790","title":"Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2605.05739","title":"Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2606.12924","title":"Iterating Toward Better Search: A Two-Agent Simulation Framework for Evaluating Agentic Search Architectures in E-Commerce","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2606.00931","title":"CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2606.17453","title":"MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision Factors","created":"2026-06-16","cited_by_count":0,"area":"agents"},{"id":"2606.26346","title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","created":"2026-06-24","cited_by_count":0,"area":"agents"}],"next_cursor":null}