{"total":29,"rows":[{"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":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247,"area":"lr"},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70,"area":"lr"},{"id":"2312.11508","title":"Rethinking the Instruction Quality: LIFT is What You Need","created":"2023-12-12","cited_by_count":34,"area":"lr"},{"id":"2411.04329","title":"CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models","created":"2024-11-07","cited_by_count":34,"area":"lr"},{"id":"2402.04858","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","created":"2024-02-07","cited_by_count":23,"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":"2503.02103","title":"Superficial Self-Improved Reasoners Benefit from Model Merging","created":"2025-03-03","cited_by_count":16,"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":"2305.18170","title":"Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning","created":"2023-05-29","cited_by_count":11,"area":"lr"},{"id":"2310.04484","title":"Ada-Instruct: Adapting Instruction Generators for Complex Reasoning","created":"2023-10-06","cited_by_count":11,"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":"2312.15960","title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","created":"2023-12-26","cited_by_count":9,"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":"2408.12337","title":"Fine-tuning Smaller Language Models for Question Answering over Financial Documents","created":"2024-08-22","cited_by_count":8,"area":"lr"},{"id":"2512.22469","title":"GraphLocator: Graph-guided Causal Reasoning for Issue Localization","created":"2025-12-27","cited_by_count":4,"area":"lr"},{"id":"2410.23402","title":"VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning","created":"2024-10-30","cited_by_count":3,"area":"lr"},{"id":"2506.01374","title":"REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving","created":"2025-06-02","cited_by_count":3,"area":"lr"},{"id":"2508.20729","title":"Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision","created":"2025-08-28","cited_by_count":2,"area":"lr"},{"id":"2310.16713","title":"SkyMath: Technical Report","created":"2023-10-25","cited_by_count":1,"area":"lr"},{"id":"2510.17158","title":"Integrating Performance Tools in Model Reasoning for GPU Kernel Optimization","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2505.17481","title":"MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning","created":"2025-05-23","cited_by_count":0,"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":"2602.14054","title":"LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2607.07619","title":"Rethinking Code Performance Benchmarks for LLMs","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2610.01936","title":"Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}