{"total":42,"rows":[{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203,"area":"lr"},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2505.15431","title":"Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought","created":"2025-05-21","cited_by_count":29,"area":"lr"},{"id":"2406.01006","title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","created":"2024-06-03","cited_by_count":27,"area":"lr"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2506.16395","title":"OJBench: A Competition Level Code Benchmark For Large Language Models","created":"2025-06-19","cited_by_count":26,"area":"lr"},{"id":"2502.03860","title":"BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation","created":"2025-02-06","cited_by_count":23,"area":"lr"},{"id":"2407.07053","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","created":"2024-07-09","cited_by_count":21,"area":"lr"},{"id":"2403.17218","title":"To Err is Machine: Vulnerability Detection Challenges LLM Reasoning","created":"2024-03-25","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":"2508.11016","title":"CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention","created":"2025-08-14","cited_by_count":18,"area":"lr"},{"id":"2406.12050","title":"Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning","created":"2024-06-17","cited_by_count":15,"area":"lr"},{"id":"2409.12929","title":"LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning","created":"2024-09-19","cited_by_count":14,"area":"lr"},{"id":"2504.06214","title":"From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models","created":"2025-04-08","cited_by_count":14,"area":"lr"},{"id":"2502.10857","title":"Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation","created":"2025-02-15","cited_by_count":12,"area":"lr"},{"id":"2512.09619","title":"GLaD: Geometric Latent Distillation for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":11,"area":"lr"},{"id":"2509.19894","title":"PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning","created":"2025-09-24","cited_by_count":9,"area":"lr"},{"id":"2507.04391","title":"Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?","created":"2025-07-06","cited_by_count":7,"area":"lr"},{"id":"2510.11769","title":"GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"id":"2603.11226","title":"ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning","created":"2026-03-11","cited_by_count":6,"area":"lr"},{"id":"2510.15079","title":"Assessing Coherency and Consistency of Code Execution Reasoning by Large Language Models","created":"2025-10-16","cited_by_count":5,"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":"2506.18421","title":"TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models","created":"2025-06-23","cited_by_count":3,"area":"lr"},{"id":"2602.08167","title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.21465","title":"DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2606.10385","title":"Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2502.11901","title":"Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2505.10594","title":"CRPE: Expanding The Reasoning Capability of Large Language Model for Code Generation","created":"2025-05-15","cited_by_count":2,"area":"lr"},{"id":"2412.12163","title":"Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!","created":"2024-12-11","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":"2511.02197","title":"Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs","created":"2025-11-04","cited_by_count":1,"area":"lr"},{"id":"2601.21894","title":"Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoning","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2603.19310","title":"MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2412.19638","title":"Xmodel-2 Technical Report","created":"2024-12-27","cited_by_count":0,"area":"lr"},{"id":"2512.00127","title":"Generating Verifiable Chain of Thoughts from Exection-Traces","created":"2025-11-28","cited_by_count":0,"area":"lr"},{"id":"2609.33463","title":"Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}