{"total":1169,"rows":[{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500,"area":null},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2502.13138","title":"AIDE: AI-Driven Exploration in the Space of Code","created":"2025-02-18","cited_by_count":226,"area":null},{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220,"area":null},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"area":null},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2506.13651","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","created":"2025-06-16","cited_by_count":120,"area":null},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105,"area":null},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101,"area":null},{"id":"2403.16971","title":"AIOS: LLM Agent Operating System","created":"2024-03-25","cited_by_count":97,"area":null},{"id":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91,"area":null},{"id":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91,"area":null},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2506.02548","title":"CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale","created":"2025-06-03","cited_by_count":78,"area":null},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76,"area":null},{"id":"2404.00599","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-03-31","cited_by_count":72,"area":null},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72,"area":null},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2502.02673","title":"MedRAX: Medical Reasoning Agent for Chest X-ray","created":"2025-02-04","cited_by_count":70,"area":null},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65,"area":null},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2603.25723","title":"Natural-Language Agent Harnesses","created":"2026-03-26","cited_by_count":61,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"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,"area":null},{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2412.01769","title":"Commit0: Library Generation from Scratch","created":"2024-12-02","cited_by_count":52,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49,"area":null},{"id":"2312.12450","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","created":"2023-12-11","cited_by_count":48,"area":null},{"id":"2506.12469","title":"Levels of Autonomy for AI Agents","created":"2025-06-14","cited_by_count":48,"area":null},{"id":"2606.14249","title":"HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry","created":"2026-06-12","cited_by_count":47,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null},{"id":"2403.08604","title":"Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study","created":"2024-03-13","cited_by_count":44,"area":null},{"id":"2504.10374","title":"Ctrl-Z: Controlling AI Agents via Resampling","created":"2025-04-14","cited_by_count":44,"area":null},{"id":"2511.03773","title":"Scaling Agent Learning via Experience Synthesis","created":"2025-11-05","cited_by_count":44,"area":null},{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43,"area":null},{"id":"2507.04952","title":"ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation","created":"2025-07-07","cited_by_count":42,"area":null},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"area":null},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2511.02817","title":"Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities","created":"2025-11-04","cited_by_count":40,"area":null},{"id":"2412.10999","title":"Cocoa: Co-Planning and Co-Execution with AI Agents","created":"2024-12-14","cited_by_count":39,"area":null},{"id":"2412.21199","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","created":"2024-12-30","cited_by_count":39,"area":null},{"id":"2502.13681","title":"Repo2Run: Automated Building Executable Environment for Code Repository at Scale","created":"2025-02-19","cited_by_count":39,"area":null},{"id":"2506.09050","title":"ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering","created":"2025-06-10","cited_by_count":39,"area":null},{"id":"2603.04370","title":"$\\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge","created":"2026-03-04","cited_by_count":39,"area":null},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2509.14252","title":"LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures","created":"2025-09-11","cited_by_count":38,"area":null},{"id":"2509.14635","title":"SWE-QA: Can Language Models Answer Repository-level Code Questions?","created":"2025-09-18","cited_by_count":38,"area":null},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38,"area":null},{"id":"2401.04757","title":"How predictable is language model benchmark performance?","created":"2024-01-09","cited_by_count":37,"area":null},{"id":"2407.10701","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2505.07897","title":"LongCodeBench: Evaluating Coding LLMs at 1M Context Windows","created":"2025-05-12","cited_by_count":37,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2310.08367","title":"MCU: An Evaluation Framework for Open-Ended Game Agents","created":"2023-10-12","cited_by_count":34,"area":null},{"id":"2402.13521","title":"Test-Driven Development for Code Generation","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2405.00253","title":"CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification","created":"2024-04-30","cited_by_count":34,"area":null},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34,"area":null},{"id":"2411.12644","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval","created":"2024-11-19","cited_by_count":34,"area":null},{"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,"area":null},{"id":"2502.18658","title":"Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support","created":"2025-02-25","cited_by_count":34,"area":null},{"id":"2505.23135","title":"VERINA: Benchmarking Verifiable Code Generation","created":"2025-05-29","cited_by_count":34,"area":null},{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2403.03129","title":"CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following","created":"2024-03-05","cited_by_count":33,"area":null},{"id":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2411.03336","title":"Towards evaluations-based safety cases for AI scheming","created":"2024-10-29","cited_by_count":33,"area":null},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2407.07565","title":"On Leakage of Code Generation Evaluation Datasets","created":"2024-07-10","cited_by_count":32,"area":null}],"next_cursor":"100"}