{"total":58,"rows":[{"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":"2603.24755","title":"SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks","created":"2026-03-25","cited_by_count":30,"area":"agents"},{"id":"2509.02360","title":"When Agents go Astray: Course-Correcting SWE Agents with PRMs","created":"2025-09-02","cited_by_count":28,"area":"agents"},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2602.11988","title":"Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?","created":"2026-02-12","cited_by_count":20,"area":"agents"},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2508.18106","title":"A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code","created":"2025-08-25","cited_by_count":14,"area":null},{"id":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"area":"agents"},{"id":"2602.21611","title":"Structurally Aligned Subtask-Level Memory for Software Engineering Agents","created":"2026-02-25","cited_by_count":12,"area":"agents"},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2603.04177","title":"CodeTaste: Can LLMs Generate Human-Level Code Refactorings?","created":"2026-03-04","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2601.11077","title":"ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development","created":"2026-01-16","cited_by_count":6,"area":"agents"},{"id":"2603.17104","title":"When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents","created":"2026-03-17","cited_by_count":6,"area":"agents"},{"id":"2509.20374","title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2602.10471","title":"TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2605.13139","title":"SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle","created":"2026-05-13","cited_by_count":5,"area":"agents"},{"id":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2603.23448","title":"Code Review Agent Benchmark","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2606.22082","title":"CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation","created":"2026-06-20","cited_by_count":4,"area":"agents"},{"id":"2507.05281","title":"CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2603.26664","title":"Learning to Commit: Generating Organic Pull Requests via Online Repository Memory","created":"2026-03-27","cited_by_count":3,"area":"agents"},{"id":"2605.06445","title":"Constraint Decay: The Fragility of LLM Agents in Backend Code Generation","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2509.25203","title":"Generating High-Quality Datasets for Code Editing via Open-Source Language Models","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2512.17387","title":"CIFE: Code Instruction-Following Evaluation","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2604.03035","title":"Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution","created":"2026-04-03","cited_by_count":2,"area":"agents"},{"id":"2605.15222","title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2607.26777","title":"CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2608.09072","title":"A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents","created":"2026-08-10","cited_by_count":2,"area":"agents"},{"id":"2603.03784","title":"Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism","created":"2026-03-04","cited_by_count":1,"area":"wm"},{"id":"2604.03632","title":"Persistent Cross-Attempt State Optimization for Repository-Level Code Generation","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2605.06279","title":"Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2607.28591","title":"Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2609.21293","title":"GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2609.37143","title":"LoLBench: Evaluating Coding Agents with Long-Horizon Proposals on Large Software Systems","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2508.20119","title":"LLM Agents for Generating Microservice-based Applications: how complex is your specification?","created":"2025-08-22","cited_by_count":0,"area":"agents"},{"id":"2601.21649","title":"SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning","created":"2026-01-29","cited_by_count":0,"area":"agents"},{"id":"2604.03622","title":"Toward Executable Repository-Level Code Generation via Environment Alignment","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.04226","title":"SW-$A^2$-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web","created":"2026-04-05","cited_by_count":0,"area":"agents"},{"id":"2605.27492","title":"Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2605.29054","title":"Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.18293","title":"Vibe Coding Ate My Homework: An evaluation of AI approaches to greenfield software engineering and programming","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.18733","title":"SWE-Future: Forecast-Conditioned Data Synthesis for Future-Oriented Software Engineering Agents","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2607.00700","title":"LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.07619","title":"Rethinking Code Performance Benchmarks for LLMs","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2607.14573","title":"Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents","created":"2026-07-16","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":"2609.01271","title":"What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels Reveal","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.26480","title":"FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.28449","title":"Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.32662","title":"AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37233","title":"DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04658","title":"RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}