{"total":59,"rows":[{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"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":"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":"2603.03823","title":"SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration","created":"2026-03-04","cited_by_count":23,"area":"agents"},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"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":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2606.30573","title":"SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions","created":"2026-06-29","cited_by_count":11,"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":"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":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"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":"2608.09802","title":"SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring","created":"2026-08-10","cited_by_count":6,"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":"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":"2605.06068","title":"VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?","created":"2026-05-07","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":"2609.01481","title":"Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement","created":"2026-09-01","cited_by_count":4,"area":"agents"},{"id":"2601.06268","title":"Automated QoR improvement in OpenROAD with coding agents","created":"2026-01-09","cited_by_count":3,"area":"agents"},{"id":"2602.09447","title":"SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents","created":"2026-02-10","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":"2608.02499","title":"SWE-Touch: Benchmarking Coding Agents When Users Touch the Code","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2603.27296","title":"A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2607.02440","title":"EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.03332","title":"AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches?","created":"2026-07-03","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":"2603.25697","title":"The Kitchen Loop: User-Spec-Driven Development for a Self-Evolving Codebase","created":"2026-03-26","cited_by_count":1,"area":"synth"},{"id":"2603.27745","title":"Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits","created":"2026-03-29","cited_by_count":1,"area":"agents"},{"id":"2604.19827","title":"More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems","created":"2026-04-20","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":"2605.15229","title":"PBT-Bench: Benchmarking AI Agents on Property-Based Testing","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2606.19613","title":"StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"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":"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":"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":"2604.11535","title":"Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.02244","title":"The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents","created":"2026-05-04","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":"2608.00122","title":"Shared Organizational Memory for Enterprise Coding Agents: System Design and Deployment Snapshot","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.10450","title":"Persistent Recursive Worlds Enable Autonomous Software Evolution","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.14863","title":"Evaluating Agentic Code Repair Capabilities in Distributed Systems","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2608.21964","title":"Repo2Skill-Evo: Repository Skills Go Stale in Silence","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.12012","title":"Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.22409","title":"Contextual Causality with Large Language Models: A Survey","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25804","title":"The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.26777","title":"SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving","created":"2026-09-22","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":"2609.35357","title":"Do Coding Agents Reuse Existing Code or Reinvent the Wheel?","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36319","title":"StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.04838","title":"MemTrace: State-Consistent Memory for Long-Horizon Coding Agents","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"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":"2610.10610","title":"Code Understanding is a Bottleneck for Coding Agents","created":"2026-10-07","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":"2610.12569","title":"SWE-Duel: Towards a Self-Scaling Arena for Coding Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.16402","title":"EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.16859","title":"ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17616","title":"StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18603","title":"AgentStripes: An Evidence-Graded Maturity Model for AI Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}