{"list":"other","total":74,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"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":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151},{"id":"2210.14179","title":"Practical Program Repair in the Era of Large Pre-trained Language Models","created":"2022-10-25","cited_by_count":133},{"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":"2406.04151","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","created":"2024-06-06","cited_by_count":120},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119},{"id":"2310.19923","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","created":"2023-10-30","cited_by_count":104},{"id":"2401.08500","title":"Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering","created":"2024-01-16","cited_by_count":103},{"id":"2410.06992","title":"SWE-Bench+: Enhanced Coding Benchmark for LLMs","created":"2024-10-09","cited_by_count":99},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93},{"id":"2308.10379","title":"Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models","created":"2023-08-20","cited_by_count":92},{"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":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79},{"id":"2207.08281","title":"Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning","created":"2022-07-17","cited_by_count":76},{"id":"2402.16352","title":"MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs","created":"2024-02-26","cited_by_count":72},{"id":"2310.01726","title":"Large Language Models for Test-Free Fault Localization","created":"2023-10-03","cited_by_count":67},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61},{"id":"2312.15698","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","created":"2023-12-25","cited_by_count":50},{"id":"2403.16362","title":"AgentFL: Scaling LLM-based Fault Localization to Project-Level Context","created":"2024-03-25","cited_by_count":47},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46},{"id":"2405.14365","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","created":"2024-05-23","cited_by_count":45},{"id":"2409.15637","title":"Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale","created":"2024-09-24","cited_by_count":43},{"id":"2305.14591","title":"ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers","created":"2023-05-24","cited_by_count":41},{"id":"2401.15481","title":"BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies","created":"2024-01-27","cited_by_count":36},{"id":"2408.07060","title":"Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents","created":"2024-08-13","cited_by_count":36},{"id":"2203.12755","title":"SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics","created":"2022-03-23","cited_by_count":33},{"id":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25},{"id":"2407.20898","title":"ThinkRepair: Self-Directed Automated Program Repair","created":"2024-07-30","cited_by_count":23},{"id":"2205.01859","title":"DEAR: A Novel Deep Learning-based Approach for Automated Program Repair","created":"2022-05-04","cited_by_count":22},{"id":"2306.00029","title":"CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs","created":"2023-05-31","cited_by_count":21},{"id":"2305.06156","title":"The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation","created":"2023-05-09","cited_by_count":20},{"id":"2402.19475","title":"The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?","created":"2024-02-29","cited_by_count":20},{"id":"2105.09352","title":"DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons","created":"2021-05-19","cited_by_count":17},{"id":"2206.07796","title":"FixEval: Execution-based Evaluation of Program Fixes for Programming Problems","created":"2022-06-15","cited_by_count":17},{"id":"2408.11296","title":"RePair: Automated Program Repair with Process-based Feedback","created":"2024-08-21","cited_by_count":16},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","cited_by_count":16},{"id":"2205.15479","title":"HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations","created":"2022-05-31","cited_by_count":9},{"id":"2311.03366","title":"Functional Overlap Reranking for Neural Code Generation","created":"2023-10-16","cited_by_count":9},{"id":"2401.01096","title":"Demystifying $\\mu$","created":"2024-01-02","cited_by_count":7},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3}],"next_cursor":null}