{"total":119,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195,"area":"agents"},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564,"area":"agents"},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315,"area":"agents"},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297,"area":"agents"},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282,"area":"agents"},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205,"area":"agents"},{"id":"2504.03601","title":"APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay","created":"2025-04-04","cited_by_count":167,"area":"agents"},{"id":"2401.05507","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","created":"2024-01-10","cited_by_count":140,"area":"agents"},{"id":"2310.10634","title":"OpenAgents: An Open Platform for Language Agents in the Wild","created":"2023-10-16","cited_by_count":137,"area":"agents"},{"id":"2406.12814","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","created":"2024-06-18","cited_by_count":120,"area":"agents"},{"id":"2505.20732","title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution","created":"2025-05-27","cited_by_count":73,"area":"agents"},{"id":"2310.06830","title":"Lemur: Harmonizing Natural Language and Code for Language Agents","created":"2023-10-10","cited_by_count":72,"area":"agents"},{"id":"2311.05657","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","created":"2023-11-09","cited_by_count":72,"area":"agents"},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"agents"},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56,"area":"agents"},{"id":"2410.07706","title":"AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories","created":"2024-10-10","cited_by_count":56,"area":"agents"},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2505.15216","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","created":"2025-05-21","cited_by_count":40,"area":"agents"},{"id":"2405.19425","title":"Adaptive In-conversation Team Building for Language Model Agents","created":"2024-05-29","cited_by_count":39,"area":"agents"},{"id":"2402.12914","title":"Large Language Model-based Human-Agent Collaboration for Complex Task Solving","created":"2024-02-20","cited_by_count":38,"area":"agents"},{"id":"2410.07869","title":"Benchmarking Agentic Workflow Generation","created":"2024-10-10","cited_by_count":37,"area":"agents"},{"id":"2502.00675","title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","created":"2025-02-02","cited_by_count":37,"area":"agents"},{"id":"2508.17281","title":"From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users","created":"2025-08-24","cited_by_count":32,"area":"agents"},{"id":"2409.01392","title":"ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems","created":"2024-09-02","cited_by_count":30,"area":"agents"},{"id":"2604.17870","title":"GraSP: Graph-Structured Skill Compositions for LLM Agents","created":"2026-04-20","cited_by_count":26,"area":"agents"},{"id":"2410.05434","title":"Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback","created":"2024-10-07","cited_by_count":24,"area":"agents"},{"id":"2603.03823","title":"SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration","created":"2026-03-04","cited_by_count":23,"area":"agents"},{"id":"2411.05651","title":"LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution","created":"2024-11-08","cited_by_count":20,"area":"agents"},{"id":"2502.10931","title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","created":"2025-02-15","cited_by_count":20,"area":"agents"},{"id":"2512.18950","title":"Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement","created":"2025-12-22","cited_by_count":20,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2505.00234","title":"Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks","created":"2025-05-01","cited_by_count":19,"area":"agents"},{"id":"2603.21489","title":"Effective Strategies for Asynchronous Software Engineering Agents","created":"2026-03-23","cited_by_count":16,"area":"agents"},{"id":"2507.14201","title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","created":"2025-07-14","cited_by_count":15,"area":"agents"},{"id":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2412.02776","title":"Hacking CTFs with Plain Agents","created":"2024-12-03","cited_by_count":14,"area":"agents"},{"id":"2603.11214","title":"Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios","created":"2026-03-11","cited_by_count":14,"area":"agents"},{"id":"2606.01619","title":"ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL","created":"2026-06-01","cited_by_count":14,"area":"agents"},{"id":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13,"area":"agents"},{"id":"2512.20798","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","created":"2025-12-23","cited_by_count":13,"area":"agents"},{"id":"2410.09114","title":"Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities","created":"2024-10-10","cited_by_count":12,"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":"2508.05674","title":"Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark","created":"2025-08-05","cited_by_count":12,"area":"agents"},{"id":"2510.24317","title":"Cybersecurity AI Benchmark (CAIBench): A Meta-Benchmark for Evaluating Cybersecurity AI Agents","created":"2025-10-28","cited_by_count":12,"area":"agents"},{"id":"2607.10891","title":"SETA: Scaling Environments for Terminal Agents","created":"2026-07-12","cited_by_count":12,"area":"agents"},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2511.14136","title":"Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems","created":"2025-11-18","cited_by_count":8,"area":"agents"},{"id":"2511.22254","title":"Co-Evolving Agents: Learning from Failures as Hard Negatives","created":"2025-11-27","cited_by_count":8,"area":"agents"},{"id":"2601.09822","title":"LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities","created":"2026-01-14","cited_by_count":8,"area":"agents"},{"id":"2411.13904","title":"Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning","created":"2024-11-21","cited_by_count":7,"area":"agents"},{"id":"2604.10866","title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","created":"2026-04-13","cited_by_count":7,"area":"agents"},{"id":"2605.14460","title":"Exploiting LLM Agent Supply Chains via Payload-less Skills","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2607.20911","title":"Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2608.05810","title":"When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents","created":"2026-08-06","cited_by_count":5,"area":"agents"},{"id":"2502.18525","title":"Programming with Pixels: Can Computer-Use Agents do Software Engineering?","created":"2025-02-24","cited_by_count":4,"area":"agents"},{"id":"2506.02048","title":"Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges","created":"2025-06-01","cited_by_count":4,"area":"agents"},{"id":"2506.13109","title":"Leveraging In-Context Learning for Language Model Agents","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2510.02389","title":"From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization","created":"2025-09-30","cited_by_count":4,"area":"agents"},{"id":"2510.03253","title":"Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents","created":"2025-09-26","cited_by_count":4,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2604.18718","title":"Towards Optimal Agentic Architectures for Offensive Security Tasks","created":"2026-04-20","cited_by_count":4,"area":"agents"},{"id":"2604.19533","title":"Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps","created":"2026-04-21","cited_by_count":4,"area":"agents"},{"id":"2607.27929","title":"Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training","created":"2026-07-30","cited_by_count":4,"area":"agents"},{"id":"2609.07925","title":"FrogNano: Training a 4B Coding Agent via Online Task Synthesis","created":"2026-09-07","cited_by_count":4,"area":"agents"},{"id":"2602.05523","title":"Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations","created":"2026-02-05","cited_by_count":3,"area":"agents"},{"id":"2604.27955","title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2510.12200","title":"HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities","created":"2025-10-14","cited_by_count":2,"area":"agents"},{"id":"2510.22462","title":"Learning \"Partner-Aware\" Collaborators in Multi-Party Collaboration","created":"2025-10-26","cited_by_count":2,"area":"agents"},{"id":"2512.23844","title":"From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"id":"2605.10597","title":"CrackMeBench: Binary Reverse Engineering for Agents","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.22564","title":"SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2606.14179","title":"CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward","created":"2026-06-12","cited_by_count":2,"area":"agents"},{"id":"2607.06195","title":"LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle","created":"2026-07-07","cited_by_count":2,"area":"agents"},{"id":"2607.12161","title":"Token Reduction Is Not Cost Reduction","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2607.12397","title":"Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"id":"2507.21113","title":"Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing","created":"2025-07-14","cited_by_count":1,"area":"agents"},{"id":"2510.02369","title":"AutoContext: Instance-Level Context Learning for LLM Agents","created":"2025-09-29","cited_by_count":1,"area":"agents"},{"id":"2511.21380","title":"Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions","created":"2025-11-26","cited_by_count":1,"area":"agents"},{"id":"2601.09129","title":"KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitation","created":"2026-01-14","cited_by_count":1,"area":"agents"},{"id":"2603.07496","title":"From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents","created":"2026-03-08","cited_by_count":1,"area":"agents"},{"id":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2603.11515","title":"Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems","created":"2026-03-12","cited_by_count":1,"area":"agents"},{"id":"2603.21551","title":"AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2604.27419","title":"InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?","created":"2026-04-30","cited_by_count":1,"area":"agents"},{"id":"2605.23574","title":"Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2607.22165","title":"DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.26237","title":"How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2608.27818","title":"AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics","created":"2026-08-28","cited_by_count":1,"area":"agents"},{"id":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.00243","title":"Invalidation Contracts for Cross-Episode Agent Memory","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.01056","title":"WorldBench: Culturally Grounded Benchmark for Multilingual Agents","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2609.11957","title":"Look Before You Leap: Pre-Action Verification for LLM Agents","created":"2026-08-09","cited_by_count":1,"area":"agents"},{"id":"2609.14637","title":"DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents","created":"2026-09-13","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}