{"total":127,"rows":[{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469,"area":"agents"},{"id":"2410.05080","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","created":"2024-10-07","cited_by_count":235,"area":"agents"},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169,"area":"agents"},{"id":"2410.06703","title":"ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents","created":"2024-10-09","cited_by_count":133,"area":"agents"},{"id":"2409.11363","title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","created":"2024-09-17","cited_by_count":123,"area":"agents"},{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102,"area":"agents"},{"id":"2407.13032","title":"Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems","created":"2024-07-17","cited_by_count":81,"area":"agents"},{"id":"2503.08979","title":"Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions","created":"2025-03-12","cited_by_count":77,"area":"agents"},{"id":"2503.12188","title":"Multi-Agent Systems Execute Arbitrary Malicious Code","created":"2025-03-15","cited_by_count":53,"area":"agents"},{"id":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2604.14228","title":"Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2601.14242","title":"APEX-Agents","created":"2026-01-20","cited_by_count":32,"area":"agents"},{"id":"2504.09702","title":"MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?","created":"2025-04-13","cited_by_count":28,"area":"agents"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"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":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2412.05449","title":"Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications","created":"2024-12-06","cited_by_count":19,"area":"agents"},{"id":"2602.14878","title":"Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions","created":"2026-02-16","cited_by_count":17,"area":"agents"},{"id":"2510.03204","title":"FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents","created":"2025-10-03","cited_by_count":16,"area":"agents"},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15,"area":"agents"},{"id":"2512.01939","title":"An Empirical Study of Agent Developer Practices in AI Agent Frameworks","created":"2025-12-01","cited_by_count":14,"area":"agents"},{"id":"2601.04583","title":"Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries","created":"2026-01-08","cited_by_count":13,"area":"agents"},{"id":"2602.22953","title":"General Agent Evaluation","created":"2026-02-26","cited_by_count":13,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2504.20965","title":"AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security","created":"2025-04-29","cited_by_count":10,"area":"agents"},{"id":"2510.16499","title":"Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection","created":"2025-10-18","cited_by_count":10,"area":"agents"},{"id":"2603.29139","title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents","created":"2026-03-31","cited_by_count":10,"area":"agents"},{"id":"2605.20530","title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","created":"2026-05-19","cited_by_count":10,"area":"agents"},{"id":"2408.15299","title":"TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering","created":"2024-08-27","cited_by_count":9,"area":"agents"},{"id":"2412.04093","title":"Practical Considerations for Agentic LLM Systems","created":"2024-12-05","cited_by_count":9,"area":"agents"},{"id":"2505.04345","title":"Build Agent Advocates, Not Platform Agents","created":"2025-05-07","cited_by_count":8,"area":"agents"},{"id":"2510.08847","title":"What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment","created":"2025-10-09","cited_by_count":8,"area":"agents"},{"id":"2604.15367","title":"SoK: Security of Autonomous LLM Agents in Agentic Commerce","created":"2026-04-15","cited_by_count":8,"area":"agents"},{"id":"2605.26112","title":"From Model Scaling to System Scaling: Scaling the Harness in Agentic AI","created":"2026-05-25","cited_by_count":8,"area":"agents"},{"id":"2506.03332","title":"Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows","created":"2025-06-03","cited_by_count":7,"area":"agents"},{"id":"2510.05307","title":"When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2510.11004","title":"Automating Structural Engineering Workflows with Large Language Model Agents","created":"2025-10-13","cited_by_count":6,"area":"agents"},{"id":"2605.00528","title":"SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2605.24002","title":"Harnessing AtomisticSkills for Agentic Atomistic Research","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2502.10420","title":"Position: Stop Acting Like Language Model Agents Are Normal Agents","created":"2025-02-04","cited_by_count":5,"area":"agents"},{"id":"2510.04173","title":"Open Agent Specification (Agent Spec): A Unified Representation for AI Agents","created":"2025-10-05","cited_by_count":5,"area":"agents"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2605.28840","title":"How Consistent Are LLM Agents? Measuring Behavioral Reproducibility in Multi-Step Tool-Calling Pipelines","created":"2026-04-23","cited_by_count":5,"area":"agents"},{"id":"2507.15676","title":"Agentic AI for autonomous anomaly management in complex systems","created":"2025-07-21","cited_by_count":4,"area":"agents"},{"id":"2512.02228","title":"STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls","created":"2025-12-01","cited_by_count":4,"area":"agents"},{"id":"2604.10938","title":"AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2607.06273","title":"AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2601.20617","title":"Agent Benchmarks Fail Public Sector Requirements","created":"2026-01-28","cited_by_count":3,"area":"agents"},{"id":"2602.11619","title":"When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents","created":"2026-02-12","cited_by_count":3,"area":"agents"},{"id":"2602.16844","title":"Overseeing Agents Without Constant Oversight: Challenges and Opportunities","created":"2026-02-18","cited_by_count":3,"area":"agents"},{"id":"2603.20256","title":"SciNav: A General Agent Framework for Scientific Coding Tasks","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"id":"2603.25764","title":"Confident and Wrong: Silent Semantic Failures in Coding Agents","created":"2026-03-26","cited_by_count":3,"area":"agents"},{"id":"2605.06457","title":"Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2608.16801","title":"When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding","created":"2026-08-17","cited_by_count":3,"area":"agents"},{"id":"2609.02783","title":"EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2609.29095","title":"Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents","created":"2026-09-24","cited_by_count":3,"area":"agents"},{"id":"2505.14215","title":"Safety Degradation in AI Agents","created":"2025-05-20","cited_by_count":2,"area":"agents"},{"id":"2509.05651","title":"Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks","created":"2025-09-06","cited_by_count":2,"area":"agents"},{"id":"2604.02674","title":"Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems","created":"2026-04-03","cited_by_count":2,"area":"agents"},{"id":"2604.27891","title":"In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks","created":"2026-04-30","cited_by_count":2,"area":"agents"},{"id":"2606.22678","title":"RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2609.01519","title":"When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation","created":"2026-09-01","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":"2604.14256","title":"Evaluation of Agents under Simulated AI Marketplace Dynamics","created":"2026-04-15","cited_by_count":1,"area":"agents"},{"id":"2604.22879","title":"Beyond Single-Agent Alignment: Preventing Context-Fragmented Violations in Multi-Agent Systems","created":"2026-04-24","cited_by_count":1,"area":"agents"},{"id":"2605.17548","title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2607.13080","title":"Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs","created":"2026-07-13","cited_by_count":1,"area":"agents"},{"id":"2607.27942","title":"Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.02444","title":"ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.25399","title":"Can your AI agent be cheaper? Investigating the effects of task specifications on token spend in agentic coding tasks","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2608.25937","title":"Candidate supply and answer selection shape the value of LLM judging in multi-agent systems","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.01660","title":"How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.07605","title":"Search-to-World: Evaluation of 3D World Delivery from User Request through Web Search","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2609.07785","title":"What Does an LLM-Agent Leaderboard Rank Actually Compare?","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2609.19607","title":"DeltaSelect: Affordable A/B Testing for Coding Agents","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2609.33153","title":"What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Review","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2609.34262","title":"Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2610.00917","title":"Finding the Right Fit: Model-Harness Interactions across Agent Tasks","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2504.12482","title":"Agentic AI Optimisation (AAIO): what it is, how it works, why it matters, and how to deal with it","created":"2025-04-16","cited_by_count":0,"area":"agents"},{"id":"2508.08761","title":"DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation","created":"2025-08-12","cited_by_count":0,"area":"agents"},{"id":"2511.03934","title":"PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2512.02230","title":"Benchmarking LLM Agents for Wealth-Management Workflows","created":"2025-12-01","cited_by_count":0,"area":"agents"},{"id":"2602.05289","title":"Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2604.01647","title":"Exploring Robust Multi-Agent Workflows for Environmental Data Management","created":"2026-04-02","cited_by_count":0,"area":"agents"},{"id":"2604.02770","title":"Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity","created":"2026-04-03","cited_by_count":0,"area":"agents"},{"id":"2605.10834","title":"From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.19722","title":"Measuring Safety Alignment Effects in Autonomous Security Agents","created":"2026-05-19","cited_by_count":0,"area":"agents"},{"id":"2607.02975","title":"Where Knowledge and Authority Sit Changes What an Agent Benchmark Can Resolve","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.06411","title":"RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2607.16133","title":"When Do Multi-Agent Systems Help? An Information Bottleneck Perspective","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2608.05784","title":"Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.19263","title":"The Evaluation Context Protocol (ECP): A Portable Contract for AI Agent Evaluation","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2608.20597","title":"Testing and Evaluation of Agentic AI Systems In Military Command and Control","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2608.27886","title":"Resource Constraints and Performance in Agentic AI Systems","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.01603","title":"Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.05975","title":"Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.12404","title":"VRL-Bench: Benchmarking agents on computer control tasks under finite trial budgets","created":"2026-09-11","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}