{"total":133,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2503.17332","title":"CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities","created":"2025-03-21","cited_by_count":96,"area":"agents"},{"id":"2503.09089","title":"LocAgent: Graph-Guided LLM Agents for Code Localization","created":"2025-03-12","cited_by_count":86,"area":"agents"},{"id":"2506.18824","title":"Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories","created":"2025-06-23","cited_by_count":81,"area":"lr"},{"id":"2506.02548","title":"CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale","created":"2025-06-03","cited_by_count":78,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2507.23348","title":"SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution","created":"2025-07-31","cited_by_count":53,"area":"lr"},{"id":"2511.03690","title":"The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents","created":"2025-11-05","cited_by_count":45,"area":"agents"},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2504.09246","title":"Type-Constrained Code Generation with Language Models","created":"2025-04-12","cited_by_count":35,"area":null},{"id":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34,"area":null},{"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":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2503.07701","title":"Automated Benchmark Generation for Repository-Level Coding Tasks","created":"2025-03-10","cited_by_count":29,"area":null},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29,"area":"agents"},{"id":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2502.01821","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","created":"2025-02-03","cited_by_count":22,"area":"agents"},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2511.06090","title":"SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?","created":"2025-11-08","cited_by_count":21,"area":null},{"id":"2508.13143","title":"Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks","created":"2025-08-18","cited_by_count":20,"area":"agents"},{"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":"2506.14683","title":"Unified Software Engineering Agent as AI Software Engineer","created":"2025-06-17","cited_by_count":19,"area":"agents"},{"id":"2504.12110","title":"Towards LLM Agents for Earth Observation","created":"2025-04-16","cited_by_count":17,"area":null},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16,"area":"agents"},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"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":"2508.10111","title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","created":"2025-08-13","cited_by_count":14,"area":null},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"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":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13,"area":"agents"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2601.20882","title":"DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2502.04419","title":"Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks","created":"2025-02-06","cited_by_count":9,"area":"synth"},{"id":"2502.13820","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning","created":"2025-02-19","cited_by_count":9,"area":"lr"},{"id":"2511.05931","title":"Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement","created":"2025-11-08","cited_by_count":9,"area":null},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2508.00408","title":"Benchmarking LLMs for Unit Test Generation from Real-World Functions","created":"2025-08-01","cited_by_count":8,"area":null},{"id":"2602.22764","title":"Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents","created":"2026-02-26","cited_by_count":8,"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":"2511.16004","title":"InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution","created":"2025-11-20","cited_by_count":7,"area":null},{"id":"2605.07769","title":"Coding Agents Don't Know When to Act","created":"2026-05-08","cited_by_count":7,"area":"agents"},{"id":"2510.23761","title":"TDFlow: Agentic Workflows for Test Driven Development","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2511.16858","title":"Investigating Test Overfitting on SWE-bench","created":"2025-11-20","cited_by_count":6,"area":null},{"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":"2601.19066","title":"Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2602.16819","title":"Hybrid-Gym: Training Coding Agents to Generalize Across Tasks","created":"2026-02-18","cited_by_count":6,"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":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"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":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"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":"2604.00917","title":"Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time","created":"2026-04-01","cited_by_count":5,"area":"agents"},{"id":"2607.00990","title":"SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests","created":"2026-07-01","cited_by_count":5,"area":"agents"},{"id":"2607.02032","title":"PACE: A Proxy for Agentic Capability Evaluation","created":"2026-07-02","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":"2502.06556","title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2502.18525","title":"Programming with Pixels: Can Computer-Use Agents do Software Engineering?","created":"2025-02-24","cited_by_count":4,"area":"agents"},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2509.25242","title":"A Benchmark for Localizing Code and Non-Code Issues in Software Projects","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2510.08720","title":"How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2510.09801","title":"How can we assess human-agent interactions? Case studies in software agent design","created":"2025-10-10","cited_by_count":4,"area":"agents"},{"id":"2601.13713","title":"SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2601.20886","title":"IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2602.02262","title":"OmniCode: A Benchmark for Evaluating Software Engineering Agents","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2509.25873","title":"Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs","created":"2025-09-30","cited_by_count":3,"area":"agents"},{"id":"2602.06098","title":"A Theoretical Analysis of Test-Driven Code Generation","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2607.19843","title":"Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2608.10875","title":"VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2609.02783","title":"EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2609.09133","title":"ExecCritic: Learn to Test, Test to Improve for Coding Agents","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2511.11012","title":"Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair","created":"2025-11-14","cited_by_count":2,"area":"agents"},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2507.22414","title":"AutoCodeSherpa: Symbolic Explanations in AI Coding Agents","created":"2025-07-30","cited_by_count":1,"area":"agents"},{"id":"2512.01396","title":"BackportBench: A Multilingual Benchmark for Automated Backporting of Patches","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2603.13384","title":"VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection","created":"2026-03-11","cited_by_count":1,"area":"agents"},{"id":"2603.25770","title":"ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation","created":"2026-03-26","cited_by_count":1,"area":"agents"},{"id":"2604.03245","title":"FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.16021","title":"Neurosymbolic Repo-level Code Localization","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.06125","title":"Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.11006","title":"An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning","created":"2026-05-10","cited_by_count":1,"area":"lr"},{"id":"2605.15229","title":"PBT-Bench: Benchmarking AI Agents on Property-Based Testing","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2605.16565","title":"Skim: Speculative Execution for Fast and Efficient Web Agents","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2606.25514","title":"Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution","created":"2026-06-24","cited_by_count":1,"area":"agents"},{"id":"2607.02469","title":"TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.02854","title":"EvoOtter: Evolutionary Reproduction Test Generator","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.09123","title":"ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports","created":"2026-07-10","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}