{"total":27,"rows":[{"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":"2606.01416","title":"Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems","created":"2026-05-31","cited_by_count":7,"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":"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":"2608.11386","title":"The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior","created":"2026-08-11","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":"2604.27891","title":"In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks","created":"2026-04-30","cited_by_count":2,"area":"agents"},{"id":"2605.06737","title":"A Self-Healing Framework for Reliable LLM-Based Autonomous Agents","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2606.20695","title":"How Much Coordination Gain Is Real? A Paired Noise-Floor Protocol for Multi-Agent LLM Benchmarks","created":"2026-06-15","cited_by_count":2,"area":"agents"},{"id":"2608.08413","title":"Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2608.11977","title":"Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection","created":"2026-08-12","cited_by_count":2,"area":"agents"},{"id":"2608.26195","title":"Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2605.14241","title":"Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2607.21635","title":"Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2607.25076","title":"Towards an Agent Operating System - Lessons from Classical and Cloud OS","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2608.09253","title":"SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.14680","title":"When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2609.00035","title":"SilentProbe: Measuring Silent Failure in Production APIs Used as Agent Tools","created":"2026-08-29","cited_by_count":1,"area":"agents"},{"id":"2606.31307","title":"When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2607.05773","title":"Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2608.15286","title":"No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage","created":"2026-08-15","cited_by_count":0,"area":"agents"},{"id":"2608.16411","title":"Towards Risk-free AI Agent Deployment","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2609.13582","title":"Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.19530","title":"When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent R\\'esum\\'e Screening","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2610.10062","title":"Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.15459","title":"When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.17953","title":"Agent-Reflex: Teaching Language Agents to Act Reflectively","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}