{"total":284,"rows":[{"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":"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":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130,"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":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","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":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93,"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":"2504.15257","title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","created":"2025-04-21","cited_by_count":63,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"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":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49,"area":null},{"id":"2506.06251","title":"DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation","created":"2025-06-06","cited_by_count":45,"area":null},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"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":"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":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","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":"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":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2410.03492","title":"Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores","created":"2024-10-04","cited_by_count":25,"area":null},{"id":"2505.20139","title":"StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs","created":"2025-05-26","cited_by_count":25,"area":null},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2507.03041","title":"Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards","created":"2025-07-03","cited_by_count":24,"area":null},{"id":"2509.04013","title":"On Robustness and Reliability of Benchmark-Based Evaluation of LLMs","created":"2025-09-04","cited_by_count":23,"area":null},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2512.16676","title":"DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI","created":"2025-12-18","cited_by_count":23,"area":null},{"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,"area":null},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20,"area":null},{"id":"2501.04694","title":"EpiCoder: Encompassing Diversity and Complexity in Code Generation","created":"2025-01-08","cited_by_count":20,"area":null},{"id":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2502.19166","title":"CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"area":null},{"id":"2506.06975","title":"Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2412.12140","title":"Frontier AI systems have surpassed the self-replicating red line","created":"2024-12-09","cited_by_count":17,"area":null},{"id":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2507.03253","title":"RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs","created":"2025-07-04","cited_by_count":17,"area":null},{"id":"2408.09121","title":"Selective Prompt Anchoring for Code Generation","created":"2024-08-17","cited_by_count":16,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2502.19852","title":"ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments","created":"2025-02-27","cited_by_count":14,"area":null},{"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,"area":null},{"id":"2505.20538","title":"AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy","created":"2025-05-26","cited_by_count":13,"area":null},{"id":"2606.05080","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","created":"2026-06-03","cited_by_count":13,"area":null},{"id":"2410.06667","title":"Large Language Models as Code Executors: An Exploratory Study","created":"2024-10-09","cited_by_count":12,"area":null},{"id":"2410.13287","title":"PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2505.10852","title":"MatTools: Benchmarking Large Language Models for Materials Science Tools","created":"2025-05-16","cited_by_count":12,"area":null},{"id":"2508.14104","title":"You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation","created":"2025-08-17","cited_by_count":12,"area":null},{"id":"2503.13733","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2506.03887","title":"Pre$^3$: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2601.20882","title":"DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2503.14190","title":"Inferring Events from Time Series using Language Models","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2503.15554","title":"Rethinking the Evaluation of Secure Code Generation","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2503.16922","title":"RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2505.23953","title":"Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2507.15886","title":"Combining Cost-Constrained Runtime Monitors for AI Safety","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2510.23538","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","created":"2025-10-27","cited_by_count":9,"area":null},{"id":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","cited_by_count":9,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2502.02928","title":"Large Language Model Guided Self-Debugging Code Generation","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2502.17657","title":"StatLLM: A Dataset for Evaluating the Performance of Large Language Models in Statistical Analysis","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2505.16303","title":"INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2507.13290","title":"Towards Formal Verification of LLM-Generated Code from Natural Language Prompts","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2508.00408","title":"Benchmarking LLMs for Unit Test Generation from Real-World Functions","created":"2025-08-01","cited_by_count":8,"area":null},{"id":"2512.00020","title":"Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead","created":"2025-10-29","cited_by_count":8,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2503.10452","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2508.05242","title":"CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2510.02279","title":"Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2603.05863","title":"ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2606.17056","title":"The Value Axis: Language Models Encode Whether They're on the Right Track","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2411.05830","title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2503.00995","title":"Evaluating Polish linguistic and cultural competency in large language models","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2503.15450","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2503.20110","title":"Efficient Model Development through Fine-tuning Transfer","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2505.12331","title":"OSS-Bench: Benchmark Generator for Coding LLMs","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2606.19830","title":"JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines","created":"2026-06-18","cited_by_count":6,"area":null},{"id":"2408.11198","title":"Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2409.02326","title":"Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2410.16655","title":"Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2507.09866","title":"Turning the Tide: Repository-based Code Reflection","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2507.10646","title":"CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance","created":"2025-07-14","cited_by_count":5,"area":null}],"next_cursor":"100"}