{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","created":"2025-05-29","cited_by_count":356},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169},{"id":"2501.15383","title":"Qwen2.5-1M Technical Report","created":"2025-01-26","cited_by_count":164},{"id":"2304.00385","title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","created":"2023-04-01","cited_by_count":125},{"id":"2209.11515","title":"Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction","created":"2022-09-23","cited_by_count":111},{"id":"2410.06992","title":"SWE-Bench+: Enhanced Coding Benchmark for LLMs","created":"2024-10-09","cited_by_count":99},{"id":"2501.10893","title":"Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments","created":"2025-01-18","cited_by_count":95},{"id":"2507.06229","title":"Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving","created":"2025-07-08","cited_by_count":94},{"id":"2510.02387","title":"CWM: An Open-Weights LLM for Research on Code Generation with World Models","created":"2025-09-30","cited_by_count":93},{"id":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91},{"id":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91},{"id":"2501.05040","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","created":"2025-01-09","cited_by_count":90},{"id":"2508.02085","title":"SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents","created":"2025-08-04","cited_by_count":69},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58},{"id":"2503.06680","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","created":"2025-03-09","cited_by_count":58},{"id":"2410.00752","title":"TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark","created":"2024-10-01","cited_by_count":52},{"id":"2503.15223","title":"Are \"Solved Issues\" in SWE-bench Really Solved Correctly? An Empirical Study","created":"2025-03-19","cited_by_count":49},{"id":"2506.12286","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","created":"2025-06-14","cited_by_count":49},{"id":"2506.11425","title":"Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards","created":"2025-06-13","cited_by_count":42},{"id":"2306.10998","title":"RepoFusion: Training Code Models to Understand Your Repository","created":"2023-06-19","cited_by_count":40},{"id":"2107.08147","title":"AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning","created":"2021-07-16","cited_by_count":39},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37},{"id":"2507.12415","title":"SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?","created":"2025-07-16","cited_by_count":36},{"id":"2508.03501","title":"Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":36},{"id":"2506.10484","title":"EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair","created":"2025-06-12","cited_by_count":35},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34},{"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},{"id":"2509.08724","title":"SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories","created":"2025-09-10","cited_by_count":31},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30},{"id":"2503.07701","title":"Automated Benchmark Generation for Repository-Level Coding Tasks","created":"2025-03-10","cited_by_count":29},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28},{"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},{"id":"2503.21710","title":"Enhancing repository-level software repair via repository-aware knowledge graphs","created":"2025-03-27","cited_by_count":27},{"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},{"id":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25},{"id":"2506.03011","title":"Coding Agents with Multimodal Browsing are Generalist Problem Solvers","created":"2025-06-03","cited_by_count":25},{"id":"2506.23749","title":"A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications","created":"2025-06-30","cited_by_count":25},{"id":"2505.04606","title":"OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution","created":"2025-05-07","cited_by_count":24},{"id":"2510.04905","title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","created":"2025-10-06","cited_by_count":23},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22},{"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},{"id":"2511.06090","title":"SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?","created":"2025-11-08","cited_by_count":21},{"id":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20},{"id":"2510.01003","title":"Improving Code Localization with Repository Memory","created":"2025-10-01","cited_by_count":20},{"id":"2503.16320","title":"Issue2Test: Generating Reproducing Test Cases from Issue Reports","created":"2025-03-20","cited_by_count":18},{"id":"2505.23604","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","created":"2025-05-29","cited_by_count":17},{"id":"2411.18015","title":"AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions","created":"2024-11-27","cited_by_count":16},{"id":"2507.00014","title":"SWE-Bench-CL: Continual Learning for Coding Agents","created":"2025-06-13","cited_by_count":14},{"id":"2505.18955","title":"Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models","created":"2025-05-25","cited_by_count":12},{"id":"2506.16136","title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","created":"2025-06-19","cited_by_count":12},{"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},{"id":"2411.01114","title":"Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage","created":"2024-11-02","cited_by_count":11},{"id":"2507.17542","title":"AssertFlip: Reproducing Bugs via Inversion of LLM-Generated Passing Tests","created":"2025-07-23","cited_by_count":11},{"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},{"id":"2412.17315","title":"CodeV: Issue Resolving with Visual Data","created":"2024-12-23","cited_by_count":9},{"id":"2505.08120","title":"Putting It All into Context: Simplifying Agents with LCLMs","created":"2025-05-12","cited_by_count":9},{"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},{"id":"2511.05931","title":"Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement","created":"2025-11-08","cited_by_count":9},{"id":"2403.00539","title":"DyPyBench: A Benchmark of Executable Python Software","created":"2024-03-01","cited_by_count":7},{"id":"2407.17631","title":"BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning","created":"2024-07-24","cited_by_count":7},{"id":"2505.10887","title":"InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction","created":"2025-05-16","cited_by_count":7},{"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},{"id":"2510.18270","title":"Can Old Tests Do New Tricks for Resolving SWE Issues?","created":"2025-10-21","cited_by_count":7},{"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},{"id":"2310.07128","title":"CrashTranslator: Automatically Reproducing Mobile Application Crashes Directly from Stack Trace","created":"2023-10-11","cited_by_count":6},{"id":"2505.00144","title":"When Deep Learning Meets Information Retrieval-based Bug Localization: A Survey","created":"2025-04-30","cited_by_count":6},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6},{"id":"2509.01616","title":"Automated Generation of Issue-Reproducing Tests by Combining LLMs and Search-Based Testing","created":"2025-09-01","cited_by_count":5},{"id":"2512.20482","title":"SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization","created":"2025-12-23","cited_by_count":5},{"id":"2412.19031","title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","created":"2024-12-26","cited_by_count":4},{"id":"2506.12728","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","created":"2025-06-15","cited_by_count":4},{"id":"2506.20081","title":"SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization","created":"2025-06-25","cited_by_count":4},{"id":"2509.25242","title":"A Benchmark for Localizing Code and Non-Code Issues in Software Projects","created":"2025-09-26","cited_by_count":4},{"id":"2403.05059","title":"Bug Priority Change: An Empirical Study on Apache Projects","created":"2024-03-08","cited_by_count":3},{"id":"2409.11190","title":"SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer","created":"2024-09-17","cited_by_count":3},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","cited_by_count":3}],"next_cursor":null}