{"total":65,"rows":[{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"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":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","cited_by_count":22,"area":"agents"},{"id":"2603.03194","title":"BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?","created":"2026-03-03","cited_by_count":22,"area":"agents"},{"id":"2608.01964","title":"LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks","created":"2026-08-03","cited_by_count":13,"area":"agents"},{"id":"2602.01655","title":"ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development","created":"2026-02-02","cited_by_count":12,"area":"agents"},{"id":"2606.16038","title":"Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents","created":"2026-06-14","cited_by_count":10,"area":"agents"},{"id":"2605.24110","title":"EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions","created":"2026-05-22","cited_by_count":9,"area":"agents"},{"id":"2603.13428","title":"SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution","created":"2026-03-13","cited_by_count":8,"area":null},{"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":"2606.26300","title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","created":"2026-06-24","cited_by_count":8,"area":"agents"},{"id":"2605.14415","title":"SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades","created":"2026-05-14","cited_by_count":7,"area":"agents"},{"id":"2607.21217","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2604.06742","title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","created":"2026-04-08","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":"2606.11042","title":"Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields","created":"2026-06-09","cited_by_count":5,"area":"agents"},{"id":"2603.00575","title":"SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks","created":"2026-02-28","cited_by_count":4,"area":"agents"},{"id":"2605.15846","title":"RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades","created":"2026-05-15","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":"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":"2607.02606","title":"ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance","created":"2026-07-01","cited_by_count":4,"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":"2606.03889","title":"RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions","created":"2026-06-02","cited_by_count":3,"area":null},{"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":"2608.00267","title":"LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2608.19854","title":"Repo0: Design-Driven Zero-to-All Code Generation","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2603.28551","title":"\"What Did It Actually Do?\": Understanding Risk Awareness and Traceability for Computer-Use Agents","created":"2026-03-30","cited_by_count":2,"area":"agents"},{"id":"2607.27146","title":"MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2609.25611","title":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2610.07557","title":"CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?","created":"2026-10-06","cited_by_count":2,"area":null},{"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":"2604.25914","title":"DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios","created":"2026-04-28","cited_by_count":1,"area":"agents"},{"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":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2608.24252","title":"SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2609.06780","title":"Shortcutting the Fix: Identifying and Categorizing Agentic Exploits in Software Engineering Benchmarks","created":"2026-09-06","cited_by_count":1,"area":"agents"},{"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":"2607.14573","title":"Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"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":"2608.10450","title":"Persistent Recursive Worlds Enable Autonomous Software Evolution","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.29615","title":"Forward-Deployed Full-Stack Engineering for Autonomous Cloud MLOps","created":"2026-08-30","cited_by_count":0,"area":null},{"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":"2609.07784","title":"xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.19759","title":"Rethinking Multi-Agent Collaboration: When More Is Less","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.28416","title":"Agent-Editing World Model: Rethinking World Modeling for LLM Agents","created":"2026-09-23","cited_by_count":0,"area":"wm"},{"id":"2609.31587","title":"Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.32631","title":"SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"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":"2609.33848","title":"QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34378","title":"Marathoner: Ultra-Long-Horizon Autonomous Intelligence","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35236","title":"Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36730","title":"Can Agents Design Libraries for Agents?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38269","title":"Zero2Repo: Can Coding Agents Build Repositories from Scratch?","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.38335","title":"E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.04973","title":"TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.06481","title":"AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation","created":"2026-10-05","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":"2610.09079","title":"Large-scale Repository Engineering via Agent-Native Reusable Code Primitives","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.11559","title":"SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13361","title":"AgentSWE: Can Coding Agents Build the Agent You Actually Want?","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14766","title":"Last Secure Code Benchmark: Is the Code You Vibe Secure?","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.20344","title":"Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}