{"total":21,"rows":[{"id":"2605.14415","title":"SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades","created":"2026-05-14","cited_by_count":7,"area":"agents"},{"id":"2609.01481","title":"Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement","created":"2026-09-01","cited_by_count":4,"area":"agents"},{"id":"2608.00267","title":"LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2608.02499","title":"SWE-Touch: Benchmarking Coding Agents When Users Touch the Code","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2608.19854","title":"Repo0: Design-Driven Zero-to-All Code Generation","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2608.28281","title":"LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering","created":"2026-08-28","cited_by_count":3,"area":"agents"},{"id":"2605.20049","title":"Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.19613","title":"StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2608.24252","title":"SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2607.18161","title":"TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.10450","title":"Persistent Recursive Worlds Enable Autonomous Software Evolution","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.29310","title":"Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.12012","title":"Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.27321","title":"Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.35357","title":"Do Coding Agents Reuse Existing Code or Reinvent the Wheel?","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36319","title":"StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents","created":"2026-09-28","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":"2610.16402","title":"EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17616","title":"StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18206","title":"SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}