{"list":"other","total":98,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2306.02224","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","created":"2023-06-04","cited_by_count":255},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235},{"id":"2405.17935","title":"Tool Learning with Large Language Models: A Survey","created":"2024-05-28","cited_by_count":223},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152},{"id":"2403.17927","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","created":"2024-03-26","cited_by_count":134},{"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":"1711.08611","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","created":"2017-11-23","cited_by_count":126},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100},{"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":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93},{"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":"2503.09089","title":"LocAgent: Graph-Guided LLM Agents for Code Localization","created":"2025-03-12","cited_by_count":86},{"id":"2405.14918","title":"AnalogCoder: Analog Circuit Design via Training-Free Code Generation","created":"2024-05-23","cited_by_count":84},{"id":"2401.12869","title":"TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks","created":"2024-01-23","cited_by_count":75},{"id":"2402.12065","title":"WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More","created":"2024-02-19","cited_by_count":69},{"id":"2308.11396","title":"Towards an Understanding of Large Language Models in Software Engineering Tasks","created":"2023-08-22","cited_by_count":68},{"id":"2311.10372","title":"A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends","created":"2023-11-17","cited_by_count":66},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58},{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54},{"id":"2308.05487","title":"A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization","created":"2023-08-10","cited_by_count":50},{"id":"2107.07112","title":"On the Evaluation of Neural Code Summarization","created":"2021-07-15","cited_by_count":48},{"id":"2502.00350","title":"OrcaLoca: An LLM Agent Framework for Software Issue Localization","created":"2025-02-01","cited_by_count":45},{"id":"2407.19487","title":"RLCoder: Reinforcement Learning for Repository-Level Code Completion","created":"2024-07-28","cited_by_count":44},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41},{"id":"2512.18552","title":"Toward Training Superintelligent Software Agents through Self-Play SWE-RL","created":"2025-12-21","cited_by_count":40},{"id":"2108.12987","title":"CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees","created":"2021-08-30","cited_by_count":32},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31},{"id":"2103.09499","title":"Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs","created":"2021-03-17","cited_by_count":30},{"id":"2308.15276","title":"Large Language Models in Fault Localisation","created":"2023-08-29","cited_by_count":28},{"id":"2406.06918","title":"HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation","created":"2024-06-11","cited_by_count":28},{"id":"2409.15154","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","created":"2024-09-23","cited_by_count":28},{"id":"2203.02700","title":"RACE: Retrieval-Augmented Commit Message Generation","created":"2022-03-05","cited_by_count":27},{"id":"2505.04606","title":"OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution","created":"2025-05-07","cited_by_count":24},{"id":"2107.01933","title":"CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network","created":"2021-07-05","cited_by_count":22},{"id":"2204.03293","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","created":"2022-04-07","cited_by_count":22},{"id":"2503.20589","title":"What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond","created":"2025-03-26","cited_by_count":22},{"id":"2407.20042","title":"When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention","created":"2024-07-29","cited_by_count":21},{"id":"2408.13204","title":"DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation","created":"2024-08-23","cited_by_count":21},{"id":"2502.18297","title":"DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis","created":"2025-02-25","cited_by_count":21},{"id":"2107.05373","title":"On the Evaluation of Commit Message Generation Models: An Experimental Study","created":"2021-07-12","cited_by_count":20},{"id":"2410.09812","title":"Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?","created":"2024-10-13","cited_by_count":17},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15},{"id":"2310.08069","title":"Rethinking Negative Pairs in Code Search","created":"2023-10-12","cited_by_count":14},{"id":"2601.22706","title":"RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories","created":"2026-01-30","cited_by_count":14},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13},{"id":"2310.01446","title":"Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning","created":"2023-10-01","cited_by_count":12},{"id":"2401.14727","title":"SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization","created":"2024-01-26","cited_by_count":11},{"id":"2406.11589","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","created":"2024-06-17","cited_by_count":11},{"id":"2408.05542","title":"You Augment Me: Exploring ChatGPT-based Data Augmentation for Semantic Code Search","created":"2024-08-10","cited_by_count":11},{"id":"2203.15287","title":"Accelerating Code Search with Deep Hashing and Code Classification","created":"2022-03-29","cited_by_count":10},{"id":"2401.05926","title":"Using Large Language Models for Commit Message Generation: A Preliminary Study","created":"2024-01-11","cited_by_count":10},{"id":"2401.08376","title":"KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation","created":"2024-01-16","cited_by_count":10},{"id":"2404.14824","title":"Automated Commit Message Generation with Large Language Models: An Empirical Study and Beyond","created":"2024-04-23","cited_by_count":10},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10},{"id":"2208.11271","title":"Tackling Long Code Search with Splitting, Encoding, and Aggregating","created":"2022-08-24","cited_by_count":9},{"id":"2308.10759","title":"EALink: An Efficient and Accurate Pre-trained Framework for Issue-Commit Link Recovery","created":"2023-08-21","cited_by_count":9},{"id":"2208.11274","title":"Revisiting Code Search in a Two-Stage Paradigm","created":"2022-08-24","cited_by_count":8},{"id":"2308.13416","title":"SoTaNa: The Open-Source Software Development Assistant","created":"2023-08-25","cited_by_count":8},{"id":"2407.13271","title":"Identifying Smart Contract Security Issues in Code Snippets from Stack Overflow","created":"2024-07-18","cited_by_count":8},{"id":"2105.09630","title":"Enriching Query Semantics for Code Search with Reinforcement Learning","created":"2021-05-20","cited_by_count":7},{"id":"2408.06037","title":"Hyperion: Unveiling DApp Inconsistencies using LLM and Dataflow-Guided Symbolic Execution","created":"2024-08-12","cited_by_count":7},{"id":"2410.22240","title":"Are Decoder-Only Large Language Models the Silver Bullet for Code Search?","created":"2024-10-29","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":"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":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7},{"id":"2504.19444","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","created":"2025-04-28","cited_by_count":6},{"id":"2210.01425","title":"Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing","created":"2022-10-04","cited_by_count":5},{"id":"2305.04508","title":"Improving Code Search with Hard Negative Sampling Based on Fine-tuning","created":"2023-05-08","cited_by_count":5},{"id":"2508.00546","title":"SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval","created":"2025-08-01","cited_by_count":5},{"id":"2311.14901","title":"Code Search Debiasing:Improve Search Results beyond Overall Ranking Performance","created":"2023-11-25","cited_by_count":4},{"id":"2412.11728","title":"SECRET: Towards Scalable and Efficient Code Retrieval via Segmented Deep Hashing","created":"2024-12-16","cited_by_count":4}],"next_cursor":null}