{"total":25,"rows":[{"id":"2606.29957","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions","created":"2026-06-29","cited_by_count":18,"area":"agents"},{"id":"2605.29442","title":"How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions","created":"2026-05-28","cited_by_count":14,"area":"agents"},{"id":"2605.12894","title":"Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents","created":"2026-05-13","cited_by_count":10,"area":"agents"},{"id":"2606.13995","title":"Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents","created":"2026-06-12","cited_by_count":7,"area":"agents"},{"id":"2605.08366","title":"SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution","created":"2026-05-08","cited_by_count":6,"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":"2607.06140","title":"CurateEvo: Data-Curation Evolving for Agentic Post-Training","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2608.10319","title":"Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2609.04681","title":"Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2609.28919","title":"Control the Harness, Control the Cost: Routing and Governing AI Coding Agents in the Enterprise","created":"2026-09-24","cited_by_count":1,"area":"agents"},{"id":"2605.30848","title":"LLM Anonymization Against Agentic Re-Identification","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2608.11460","title":"Principal Trait Analysis: Towards Deriving \"Skills\" in Human-AI Collaboration","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.20195","title":"From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2608.27831","title":"RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2608.28378","title":"PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.17817","title":"Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.19587","title":"Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.24234","title":"The Work Behind Delegation: A Framework for Supervising AI Coding Agents","created":"2026-09-21","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":"2609.39957","title":"Learning When and How to Intervene: A Hindsight-Distilled Sentinel for Coding Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.05586","title":"AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.09633","title":"Coding-Agent Benchmarks Should Match Their Users' Task Flows","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.10610","title":"Code Understanding is a Bottleneck for Coding Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11559","title":"SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.17757","title":"Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}