{"total":47,"rows":[{"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":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2601.06112","title":"ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions","created":"2026-01-03","cited_by_count":36,"area":"agents"},{"id":"2508.00500","title":"ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction","created":"2025-08-01","cited_by_count":28,"area":"agents"},{"id":"2506.08119","title":"SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents","created":"2025-06-09","cited_by_count":23,"area":"agents"},{"id":"2310.00322","title":"Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games","created":"2023-09-30","cited_by_count":17,"area":"agents"},{"id":"2406.01623","title":"WebSuite: Systematically Evaluating Why Web Agents Fail","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"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":"2603.08806","title":"Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications","created":"2026-03-09","cited_by_count":6,"area":"agents"},{"id":"2603.23806","title":"Willful Disobedience: Automatically Detecting Failures in Agentic Traces","created":"2026-03-25","cited_by_count":6,"area":"agents"},{"id":"2606.17799","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2607.15684","title":"Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports","created":"2026-07-17","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":"2505.01592","title":"AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents","created":"2025-05-02","cited_by_count":2,"area":"agents"},{"id":"2511.03023","title":"PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2605.02463","title":"When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2605.05379","title":"Partial Evidence Bench: Benchmarking Authorization-Limited Evidence in Agentic Systems","created":"2026-05-06","cited_by_count":2,"area":"agents"},{"id":"2605.12729","title":"Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety","created":"2026-05-12","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":"2507.21188","title":"Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs","created":"2025-07-27","cited_by_count":1,"area":"agents"},{"id":"2602.02138","title":"CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems","created":"2026-02-02","cited_by_count":1,"area":"agents"},{"id":"2605.26521","title":"Testing Agentic Workflows with Structural Coverage Criteria","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2606.10933","title":"Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.19704","title":"Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2606.19749","title":"Benchmarking Agentic Review Systems","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2606.30840","title":"Contrastive Reflection for Iterative Prompt Optimization","created":"2026-06-29","cited_by_count":1,"area":"agents"},{"id":"2608.09799","title":"SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.18081","title":"Position: Behavioral Systems Require Behavioral Tests","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2601.07504","title":"FROAV: A Framework for RAG Observation and Agent Verification -- Lowering the Barrier to LLM Agent Research","created":"2026-01-12","cited_by_count":0,"area":"agents"},{"id":"2604.27586","title":"Trace-Level Analysis of Information Contamination in Multi-Agent Systems","created":"2026-04-30","cited_by_count":0,"area":"agents"},{"id":"2605.25981","title":"AgentDiff: Meaning-Bearing Rewrites Trigger Deeper Divergence than Presentation Changes in LLM Agents","created":"2026-05-25","cited_by_count":0,"area":"agents"},{"id":"2606.11686","title":"Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness","created":"2026-06-10","cited_by_count":0,"area":"agents"},{"id":"2608.03970","title":"Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.09485","title":"Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.20938","title":"No Judgment Without a Reason: Counterfactual Receipts for Versioned AI Evaluators","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.29481","title":"SIC-Agents: Benchmarking and Building an Adaptive Simulator for Pediatric Serious Illness Communication Training","created":"2026-08-30","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":"2609.29465","title":"SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories","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":"2609.33885","title":"Prospective Interpretation Risk: Principled Communication Control Between LLMs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.04168","title":"Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.04544","title":"Label Agreement Does Not Measure Authorization","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.06192","title":"Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.12792","title":"Large Language Models, Machine-Assisted Cultural Analytics, and the Agentic Turn","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.16838","title":"Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.20195","title":"What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}