{"list":"closest","total":62,"rows":[{"id":"2512.18552","title":"Toward Training Superintelligent Software Agents through Self-Play SWE-RL","created":"2025-12-21","cited_by_count":40},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59},{"id":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13},{"id":"2512.10218","title":"Does SWE-Bench-Verified Test Agent Ability or Model Memory?","created":"2025-12-11","cited_by_count":16},{"id":"2512.09543","title":"SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMs","created":"2025-12-10","cited_by_count":5},{"id":"2512.02393","title":"Process-Centric Analysis of Agentic Software Systems","created":"2025-12-02","cited_by_count":24},{"id":"2512.07850","title":"SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents","created":"2025-11-26","cited_by_count":21},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95},{"id":"2511.00197","title":"Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories","created":"2025-10-31","cited_by_count":33},{"id":"2510.21903","title":"TOM-SWE: User Mental Modeling For Software Engineering Agents","created":"2025-10-24","cited_by_count":13},{"id":"2510.21614","title":"Huxley-G\\\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine","created":"2025-10-24","cited_by_count":53},{"id":"2510.16786","title":"More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents","created":"2025-10-19","cited_by_count":8},{"id":"2510.16059","title":"SIADAFIX: issue description response for adaptive program repair","created":"2025-10-17","cited_by_count":1},{"id":"2510.11838","title":"Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling","created":"2025-10-13","cited_by_count":12},{"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},{"id":"2510.08996","title":"Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation","created":"2025-10-10","cited_by_count":15},{"id":"2509.25873","title":"Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs","created":"2025-09-30","cited_by_count":3},{"id":"2509.23586","title":"Reducing Cost of LLM Agents with Trajectory Reduction","created":"2025-09-28","cited_by_count":48},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41},{"id":"2509.13941","title":"An Empirical Study on Failures in Automated Issue Solving","created":"2025-09-17","cited_by_count":16},{"id":"2509.02360","title":"When Agents go Astray: Course-Correcting SWE Agents with PRMs","created":"2025-09-02","cited_by_count":28},{"id":"2509.25193","title":"Devstral: Fine-tuning Language Models for Coding Agent Applications","created":"2025-08-08","cited_by_count":24},{"id":"2508.01550","title":"RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale","created":"2025-08-03","cited_by_count":8},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94},{"id":"2507.23348","title":"SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution","created":"2025-07-31","cited_by_count":53},{"id":"2506.19290","title":"Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs","created":"2025-06-24","cited_by_count":26},{"id":"2506.18824","title":"Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories","created":"2025-06-23","cited_by_count":81},{"id":"2506.17772","title":"PAGENT: Learning to Patch Software Engineering Agents","created":"2025-06-21","cited_by_count":4},{"id":"2506.16650","title":"SemAgent: A Semantics Aware Program Repair Agent","created":"2025-06-19","cited_by_count":9},{"id":"2506.09289","title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","created":"2025-06-10","cited_by_count":45},{"id":"2506.07636","title":"SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling","created":"2025-06-09","cited_by_count":26},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25},{"id":"2505.20411","title":"SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents","created":"2025-05-26","cited_by_count":142},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285},{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85},{"id":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26},{"id":"2503.18455","title":"SEAlign: Alignment Training for Software Engineering Agent","created":"2025-03-24","cited_by_count":11},{"id":"2503.14269","title":"DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal","created":"2025-03-18","cited_by_count":20},{"id":"2503.12374","title":"Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios","created":"2025-03-16","cited_by_count":14},{"id":"2503.09089","title":"LocAgent: Graph-Guided LLM Agents for Code Localization","created":"2025-03-12","cited_by_count":86},{"id":"2502.13069","title":"Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering","created":"2025-02-18","cited_by_count":38},{"id":"2502.01821","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","created":"2025-02-03","cited_by_count":22},{"id":"2502.00350","title":"OrcaLoca: An LLM Agent Framework for Software Issue Localization","created":"2025-02-01","cited_by_count":45},{"id":"2501.16655","title":"Large Language Model Critics for Execution-Free Evaluation of Code Changes","created":"2025-01-28","cited_by_count":7},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336},{"id":"2411.10213","title":"An Empirical Study on LLM-based Agents for Automated Bug Fixing","created":"2024-11-15","cited_by_count":23},{"id":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61},{"id":"2410.20285","title":"SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement","created":"2024-10-26","cited_by_count":132},{"id":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178},{"id":"2409.00899","title":"MarsCode Agent: AI-native Automated Bug Fixing","created":"2024-09-02","cited_by_count":71},{"id":"2408.07060","title":"Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents","created":"2024-08-13","cited_by_count":36},{"id":"2408.02232","title":"SpecRover: Code Intent Extraction via LLMs","created":"2024-08-05","cited_by_count":72},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133},{"id":"2406.11638","title":"MASAI: Modular Architecture for Software-engineering AI Agents","created":"2024-06-17","cited_by_count":49},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2403.17927","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","created":"2024-03-26","cited_by_count":134},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232}],"next_cursor":null}