{"total":30,"rows":[{"id":"2607.07946","title":"DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks","created":"2026-07-08","cited_by_count":49,"area":"agents"},{"id":"2512.10218","title":"Does SWE-Bench-Verified Test Agent Ability or Model Memory?","created":"2025-12-11","cited_by_count":16,"area":"agents"},{"id":"2510.08996","title":"Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2507.15003","title":"The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering","created":"2025-07-20","cited_by_count":9,"area":"agents"},{"id":"2506.17208","title":"Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems","created":"2025-06-20","cited_by_count":8,"area":"agents"},{"id":"2507.18755","title":"Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback","created":"2025-07-24","cited_by_count":6,"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":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"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":"2607.06184","title":"What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents","created":"2026-07-07","cited_by_count":5,"area":"agents"},{"id":"2608.23564","title":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","created":"2026-08-24","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":"2604.12147","title":"From Plan to Action: How Well Do Agents Follow the Plan?","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2510.17925","title":"SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion","created":"2025-10-20","cited_by_count":3,"area":"agents"},{"id":"2606.17799","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","created":"2026-06-16","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":"2608.28281","title":"LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering","created":"2026-08-28","cited_by_count":3,"area":"agents"},{"id":"2606.22417","title":"Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2606.24820","title":"SHERLOC: Structured Diagnostic Localization for Code Repair Agents","created":"2026-06-23","cited_by_count":2,"area":"agents"},{"id":"2602.18571","title":"Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?","created":"2026-02-20","cited_by_count":1,"area":"agents"},{"id":"2604.20811","title":"Diagnosing CFG Interpretation in LLMs","created":"2026-04-22","cited_by_count":1,"area":"agents"},{"id":"2607.07593","title":"What Makes a Good Bug Report for an AI Agent?","created":"2026-07-08","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2607.06411","title":"RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications","created":"2026-07-07","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":"2609.17394","title":"Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.27891","title":"Schr\\\"odinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.36161","title":"From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.05830","title":"Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}