{"total":75,"rows":[{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"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":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2502.13681","title":"Repo2Run: Automated Building Executable Environment for Code Repository at Scale","created":"2025-02-19","cited_by_count":39,"area":null},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"area":null},{"id":"2512.17419","title":"SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories","created":"2025-12-19","cited_by_count":28,"area":null},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"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":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20,"area":null},{"id":"2510.22780","title":"How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations","created":"2025-10-26","cited_by_count":19,"area":null},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2603.13023","title":"daVinci-Env: Open SWE Environment Synthesis at Scale","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2606.05080","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","created":"2026-06-03","cited_by_count":13,"area":null},{"id":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","cited_by_count":12,"area":null},{"id":"2506.08140","title":"AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists","created":"2025-06-09","cited_by_count":11,"area":null},{"id":"2507.11059","title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks","created":"2025-07-15","cited_by_count":9,"area":null},{"id":"2603.13428","title":"SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution","created":"2026-03-13","cited_by_count":8,"area":null},{"id":"2609.04148","title":"Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments","created":"2026-09-03","cited_by_count":8,"area":null},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2608.13951","title":"HELIX: Model-Harness Co-evolution for Recursive Self-Improvement","created":"2026-08-14","cited_by_count":7,"area":null},{"id":"2601.13384","title":"From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2604.11716","title":"SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context","created":"2026-04-13","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2510.03178","title":"When Names Disappear: Revealing What LLMs Actually Understand About Code","created":"2025-10-03","cited_by_count":4,"area":null},{"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":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2604.14624","title":"Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2608.27449","title":"SWE-Prime: Fewer Trajectories, Better Performance","created":"2026-08-27","cited_by_count":4,"area":null},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2608.03571","title":"Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2608.22808","title":"CatchBench: When Can an Agent Failure Be Caught?","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2608.08570","title":"FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents","created":"2026-08-09","cited_by_count":2,"area":null},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2610.07557","title":"CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?","created":"2026-10-06","cited_by_count":2,"area":null},{"id":"2602.07457","title":"Pull Requests as a Training Signal for Repo-Level Code Editing","created":"2026-02-07","cited_by_count":1,"area":null},{"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":"2604.27977","title":"D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2607.28587","title":"PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.11341","title":"Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2610.02710","title":"Self-Supervised Scaling of Terminal Environments for Scientific Domains","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2610.02826","title":"Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2610.10426","title":"CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution","created":"2026-10-07","cited_by_count":1,"area":null},{"id":"2601.18119","title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2605.11030","title":"An Executable Benchmarking Suite for Tool-Using Agents","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.29115","title":"unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.04141","title":"Efficient Test-Time Adaptation through Human-AI Interaction","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.20715","title":"Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.32391","title":"SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation","created":"2026-09-26","cited_by_count":0,"area":null},{"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":"2609.33023","title":"SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33772","title":"Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35290","title":"EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37082","title":"Traverse: Learning When to Remember, Reset, and Redirect for Long-Horizon Web Search","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38606","title":"SecureVibe: Making Vibe Coding More Secure","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},{"id":"2610.07832","title":"Harness Engineering for Software Engineering via Modular Executable Dev-Primitives","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.15345","title":"CodeWalk: Generating Coding Benchmarks by Walking a Problem Graph","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16397","title":"Recursive Environment Scaling for General Long-Horizon Agents","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17175","title":"FunDM: Cheap & Label-Free Decision Models from Frozen Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.20038","title":"SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20256","title":"Long-Horizon RL Needs Muon","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}