{"total":33,"rows":[{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625,"area":"lr"},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239,"area":"lr"},{"id":"2405.11403","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","created":"2024-05-18","cited_by_count":177,"area":"lr"},{"id":"2210.07128","title":"Language Models of Code are Few-Shot Commonsense Learners","created":"2022-10-13","cited_by_count":160,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2306.00108","title":"Better patching using LLM prompting, via Self-Consistency","created":"2023-05-31","cited_by_count":29,"area":"lr"},{"id":"2410.01999","title":"CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs","created":"2024-10-02","cited_by_count":18,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2403.13271","title":"Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs","created":"2024-03-20","cited_by_count":17,"area":"lr"},{"id":"2405.17057","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation","created":"2024-05-27","cited_by_count":14,"area":"lr"},{"id":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2404.16333","title":"AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation","created":"2024-04-25","cited_by_count":10,"area":"lr"},{"id":"2408.10918","title":"CHECKWHY: Causal Fact Verification via Argument Structure","created":"2024-08-20","cited_by_count":9,"area":"lr"},{"id":"2508.05710","title":"Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning","created":"2025-08-07","cited_by_count":9,"area":"lr"},{"id":"2309.16436","title":"Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving","created":"2023-09-28","cited_by_count":6,"area":"lr"},{"id":"2412.02906","title":"Does Few-Shot Learning Help LLM Performance in Code Synthesis?","created":"2024-12-03","cited_by_count":6,"area":"lr"},{"id":"2510.18863","title":"EffiReasonTrans: RL-Optimized Reasoning for Code Translation","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2601.18044","title":"RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models","created":"2026-01-25","cited_by_count":5,"area":"lr"},{"id":"2603.09678","title":"EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages","created":"2026-03-10","cited_by_count":4,"area":"lr"},{"id":"2405.03509","title":"Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context Learning","created":"2024-05-06","cited_by_count":2,"area":"lr"},{"id":"2512.22633","title":"Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair","created":"2025-12-27","cited_by_count":2,"area":"lr"},{"id":"2606.09396","title":"PriFT: Prior-Support Guided Supervised Fine-Tuning","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2210.08548","title":"Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samples","created":"2022-10-16","cited_by_count":1,"area":"lr"},{"id":"2509.21170","title":"Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2506.21211","title":"$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models","created":"2025-06-26","cited_by_count":0,"area":"lr"},{"id":"2507.18476","title":"Automated Code Review Using Large Language Models with Symbolic Reasoning","created":"2025-07-24","cited_by_count":0,"area":"lr"},{"id":"2509.15690","title":"CCrepairBench: A High-Fidelity Benchmark and Reinforcement Learning Framework for C++ Compilation Repair","created":"2025-09-19","cited_by_count":0,"area":"lr"},{"id":"2509.17337","title":"LLaVul: A Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code","created":"2025-09-22","cited_by_count":0,"area":"lr"},{"id":"2511.17027","title":"ReVul-CoT: Towards Effective Software Vulnerability Assessment with Retrieval-Augmented Generation and Chain-of-Thought Prompting","created":"2025-11-21","cited_by_count":0,"area":"lr"},{"id":"2604.27096","title":"Think it, Run it: Autonomous ML pipeline generation via self-healing multi-agent AI","created":"2026-04-29","cited_by_count":0,"area":"lr"},{"id":"2605.03227","title":"Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs","created":"2026-05-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}