{"total":47,"rows":[{"id":"2412.00154","title":"o1-Coder: an o1 Replication for Coding","created":"2024-11-29","cited_by_count":78,"area":null},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"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":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"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":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30,"area":null},{"id":"2409.18433","title":"Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization","created":"2024-09-27","cited_by_count":24,"area":null},{"id":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2404.03543","title":"CodeEditorBench: Evaluating Code Editing Capability of Large Language Models","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2407.21077","title":"Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models","created":"2024-07-29","cited_by_count":19,"area":null},{"id":"2503.05453","title":"Soft Policy Optimization: Online Off-Policy RL for Sequence Models","created":"2025-03-07","cited_by_count":12,"area":null},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","cited_by_count":11,"area":null},{"id":"2510.12803","title":"AutoCode: LLMs as Problem Setters for Competitive Programming","created":"2025-09-29","cited_by_count":11,"area":null},{"id":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2409.03810","title":"How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2510.18731","title":"Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards","created":"2025-10-21","cited_by_count":6,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2507.12284","title":"MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2605.04970","title":"Skill Neologisms: Towards Skill-based Continual Learning","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.24812","title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2505.12925","title":"CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2609.04061","title":"When Models Edit Too Much: On the Fidelity of Minimal Code Edits","created":"2026-09-03","cited_by_count":3,"area":null},{"id":"2501.05601","title":"Exploring Large Language Models for Translating Romanian Computational Problems into English","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2602.00166","title":"Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2605.28751","title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.12864","title":"Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2509.20837","title":"Verification Limits Code LLM Training","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2604.27467","title":"ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.04615","title":"Beyond Retrieval: A Multitask Benchmark and Model for Code Search","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.28022","title":"Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.31058","title":"Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.22676","title":"How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2609.03955","title":"Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2409.09054","title":"Evaluating the Performance of Large Language Models in Competitive Programming: A Multi-Year, Multi-Grade Analysis","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2411.15470","title":"A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.13217","title":"VeRA: Renewing Reasoning Benchmarks with Executable Specifications","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2606.07527","title":"Post-training is (Massive) Supervised Learning","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2608.23632","title":"Function-Level Execution Feedback for Code Preference Optimization","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.09135","title":"Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.16648","title":"GrowMTP: Can RL Grow Its Own Draft Head?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.19705","title":"RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}