{"total":17,"rows":[{"id":"2602.10975","title":"FeatureBench: Benchmarking Agentic Coding for Complex Feature Development","created":"2026-02-11","cited_by_count":34,"area":"agents"},{"id":"2602.14337","title":"LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces","created":"2026-02-15","cited_by_count":34,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2608.14380","title":"AgentRewind: Recoverable Execution for Long-Horizon LLM Agents","created":"2026-08-14","cited_by_count":7,"area":"agents"},{"id":"2510.26852","title":"CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","cited_by_count":4,"area":"agents"},{"id":"2607.00041","title":"ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2608.08950","title":"Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework","created":"2026-08-09","cited_by_count":3,"area":"agents"},{"id":"2509.08088","title":"EnvX: Agentize Everything with Agentic AI","created":"2025-09-09","cited_by_count":2,"area":"agents"},{"id":"2604.04532","title":"Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2605.20456","title":"Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development","created":"2026-05-19","cited_by_count":2,"area":"agents"},{"id":"2606.08500","title":"Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey","created":"2026-06-07","cited_by_count":0,"area":"agents"},{"id":"2607.26451","title":"ExplainBench: Evaluating Code Explanations from Agents","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2608.01189","title":"MADE: Belief-Driven Dual-Agent Coordination for Autonomous Model Deployment","created":"2026-08-02","cited_by_count":0,"area":"agents"},{"id":"2608.30300","title":"Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.23570","title":"VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks","created":"2026-09-20","cited_by_count":0,"area":"agents"}],"next_cursor":null}