{"total":107,"rows":[{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231,"area":"agents"},{"id":"2504.01382","title":"An Illusion of Progress? Assessing the Current State of Web Agents","created":"2025-04-02","cited_by_count":174,"area":"agents"},{"id":"2504.03274","title":"Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations","created":"2025-04-04","cited_by_count":28,"area":"agents"},{"id":"2510.02554","title":"ToolTweak: An Attack on Tool Selection in LLM-based Agents","created":"2025-10-02","cited_by_count":26,"area":"agents"},{"id":"2606.26294","title":"The Red Queen G\\\"odel Machine: Co-Evolving Agents and Their Evaluators","created":"2026-06-24","cited_by_count":19,"area":"agents"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2504.18565","title":"RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents","created":"2025-04-21","cited_by_count":15,"area":"agents"},{"id":"2412.21102","title":"Exploring and Controlling Diversity in LLM-Agent Conversation","created":"2024-12-30","cited_by_count":12,"area":"agents"},{"id":"2604.22840","title":"AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards","created":"2026-04-21","cited_by_count":11,"area":"agents"},{"id":"2512.23128","title":"It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents","created":"2025-12-29","cited_by_count":10,"area":"agents"},{"id":"2601.12910","title":"SciCoQA: Quality Assurance for Scientific Paper--Code Alignment","created":"2026-01-19","cited_by_count":10,"area":"agents"},{"id":"2603.03258","title":"Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals","created":"2026-03-03","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2608.11246","title":"Towards the Harness of Embodied Agents","created":"2026-08-03","cited_by_count":9,"area":"agents"},{"id":"2503.19711","title":"Writing as a testbed for open ended agents","created":"2025-03-25","cited_by_count":8,"area":"agents"},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7,"area":"agents"},{"id":"2606.08091","title":"VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation","created":"2026-06-06","cited_by_count":7,"area":"agents"},{"id":"2406.07275","title":"DCA-Bench: A Benchmark for Dataset Curation Agents","created":"2024-06-11","cited_by_count":6,"area":"agents"},{"id":"2602.15456","title":"In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations","created":"2026-02-17","cited_by_count":6,"area":"agents"},{"id":"2506.22957","title":"Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models","created":"2025-06-28","cited_by_count":5,"area":"agents"},{"id":"2511.17085","title":"Why Do Language Model Agents Whistleblow?","created":"2025-11-21","cited_by_count":5,"area":"agents"},{"id":"2603.06874","title":"LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models","created":"2026-03-06","cited_by_count":5,"area":"agents"},{"id":"2603.20324","title":"When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines","created":"2026-03-20","cited_by_count":5,"area":"agents"},{"id":"2605.22502","title":"Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost","created":"2026-05-21","cited_by_count":5,"area":"agents"},{"id":"2605.23296","title":"Parallel Context Compaction for Long-Horizon LLM Agent Serving","created":"2026-05-22","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":"2608.23564","title":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","created":"2026-08-24","cited_by_count":5,"area":"agents"},{"id":"2607.25152","title":"When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops","created":"2026-07-27","cited_by_count":4,"area":"agents"},{"id":"2507.11198","title":"Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding","created":"2025-07-15","cited_by_count":3,"area":"agents"},{"id":"2507.19543","title":"Agent WARPP: Workflow Adherence via Runtime Parallel Personalization","created":"2025-07-23","cited_by_count":3,"area":"agents"},{"id":"2606.08867","title":"Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework","created":"2026-06-07","cited_by_count":3,"area":"agents"},{"id":"2606.27492","title":"QueenBee Planner: Skill-Evolving Communication Topologies for Token-Efficient LLM Multi-Agent Systems","created":"2026-06-25","cited_by_count":3,"area":"agents"},{"id":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2609.12191","title":"GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents","created":"2026-09-10","cited_by_count":3,"area":"agents"},{"id":"2609.12205","title":"Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents","created":"2026-09-10","cited_by_count":3,"area":"agents"},{"id":"2601.18027","title":"Sentipolis: Emotion-Aware Agents for Social Simulations","created":"2026-01-25","cited_by_count":2,"area":"agents"},{"id":"2604.01195","title":"ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget","created":"2026-04-01","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":"2606.04296","title":"The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.16710","title":"Misinformation Propagation in Benign Multi-Agent Systems","created":"2026-06-15","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":"2607.16345","title":"AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows","created":"2026-07-16","cited_by_count":2,"area":"agents"},{"id":"2607.19409","title":"FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance","created":"2026-07-11","cited_by_count":2,"area":"agents"},{"id":"2608.14825","title":"Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce","created":"2026-08-14","cited_by_count":2,"area":"agents"},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"area":"agents"},{"id":"2609.17989","title":"Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders","created":"2026-09-16","cited_by_count":2,"area":"agents"},{"id":"2411.16077","title":"SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended text","created":"2024-11-25","cited_by_count":1,"area":"agents"},{"id":"2505.20973","title":"Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement","created":"2025-05-27","cited_by_count":1,"area":"agents"},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.20855","title":"Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis","created":"2026-02-24","cited_by_count":1,"area":"agents"},{"id":"2605.17554","title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2605.20312","title":"Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.24026","title":"Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2607.18575","title":"RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2607.24604","title":"Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2608.09855","title":"The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.13564","title":"Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation","created":"2026-06-25","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":"2609.02889","title":"Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2609.18605","title":"PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?","created":"2026-09-16","cited_by_count":1,"area":"agents"},{"id":"2609.29718","title":"PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.30345","title":"Coding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations","created":"2026-09-24","cited_by_count":1,"area":"agents"},{"id":"2609.33495","title":"LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2605.24699","title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.01434","title":"DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering","created":"2026-05-31","cited_by_count":0,"area":"agents"},{"id":"2606.20632","title":"Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2606.23403","title":"Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems","created":"2026-06-22","cited_by_count":0,"area":"agents"},{"id":"2607.04576","title":"Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.18529","title":"EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.20527","title":"Evaluating and Guarding Citation Faithfulness in Agentic Scientific Synthesis","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.25485","title":"PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.04746","title":"Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems","created":"2026-08-05","cited_by_count":0,"area":"agents"},{"id":"2608.07743","title":"QuantumMind: Constraint-Grounded Agentic Reasoning for Speedup Analysis in Quantum Computing","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.08601","title":"Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents","created":"2026-08-09","cited_by_count":0,"area":"agents"},{"id":"2608.09857","title":"Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.11033","title":"Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.15877","title":"Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation","created":"2026-08-16","cited_by_count":0,"area":"agents"},{"id":"2608.28631","title":"CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science","created":"2026-08-05","cited_by_count":0,"area":"agents"},{"id":"2609.02750","title":"Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.05018","title":"How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.07611","title":"AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.14157","title":"When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"id":"2609.14758","title":"Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.16625","title":"AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.18844","title":"ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.29578","title":"PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.30471","title":"CARGO: Context-Aware Retrieval-Gated Evaluation of Agentic AI in Production","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32092","title":"On Evaluating and Improving Conversational Agents in Production","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.32379","title":"Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33017","title":"Trust and Task Completion in the World of Consumer AI Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33295","title":"TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.33717","title":"Self-Designed Evaluators and Warm Memory for Long-Horizon Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35928","title":"Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36739","title":"Frontier Autolab: Organizational Memory, Adversarial Dissent and Temporal Leakage in Multi-Agent LLM Firms Across Fifty Years of Technological Change","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39958","title":"Better Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.40103","title":"JuryFlow: Disagreement-Guided Human-in-the-Loop Multi-Agent Evaluation","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.04074","title":"IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}