{"total":117,"rows":[{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462,"area":"lr"},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988,"area":"lr"},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2408.00724","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","created":"2024-08-01","cited_by_count":290,"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":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194,"area":"lr"},{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2312.04511","title":"An LLM Compiler for Parallel Function Calling","created":"2023-12-07","cited_by_count":179,"area":"lr"},{"id":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158,"area":"lr"},{"id":"2505.00949","title":"Llama-Nemotron: Efficient Reasoning Models","created":"2025-05-02","cited_by_count":158,"area":"lr"},{"id":"2503.23829","title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains","created":"2025-03-31","cited_by_count":156,"area":"lr"},{"id":"2406.09961","title":"ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation","created":"2024-06-14","cited_by_count":129,"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":"2305.11860","title":"Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs","created":"2023-05-19","cited_by_count":115,"area":"lr"},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98,"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":"2402.01391","title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback","created":"2024-02-02","cited_by_count":77,"area":"lr"},{"id":"2506.13284","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","created":"2025-06-16","cited_by_count":77,"area":"lr"},{"id":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71,"area":"lr"},{"id":"2504.14655","title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs","created":"2025-04-20","cited_by_count":70,"area":"lr"},{"id":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64,"area":"lr"},{"id":"2506.04210","title":"Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models","created":"2025-06-04","cited_by_count":53,"area":"lr"},{"id":"2505.21297","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","created":"2025-05-27","cited_by_count":51,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2506.05817","title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","created":"2025-06-06","cited_by_count":46,"area":"lr"},{"id":"2506.11425","title":"Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards","created":"2025-06-13","cited_by_count":42,"area":"lr"},{"id":"2505.24183","title":"QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation","created":"2025-05-30","cited_by_count":35,"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":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"area":"lr"},{"id":"2310.14053","title":"Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain","created":"2023-10-21","cited_by_count":31,"area":"lr"},{"id":"2410.08105","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","created":"2024-10-10","cited_by_count":29,"area":"lr"},{"id":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"2510.11062","title":"Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs","created":"2025-10-13","cited_by_count":28,"area":"lr"},{"id":"2510.01367","title":"Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort","created":"2025-10-01","cited_by_count":27,"area":"lr"},{"id":"2409.09584","title":"RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation","created":"2024-09-15","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":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2501.10069","title":"A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks","created":"2025-01-17","cited_by_count":21,"area":"lr"},{"id":"2512.16848","title":"Meta-RL Induces Exploration in Language Agents","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2410.12854","title":"TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees","created":"2024-10-10","cited_by_count":19,"area":"lr"},{"id":"2601.09088","title":"Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning","created":"2026-01-14","cited_by_count":17,"area":"lr"},{"id":"2503.23145","title":"CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis","created":"2025-03-29","cited_by_count":16,"area":"lr"},{"id":"2502.20868","title":"ProBench: Benchmarking Large Language Models in Competitive Programming","created":"2025-02-28","cited_by_count":15,"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":"2504.14119","title":"CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning","created":"2025-04-19","cited_by_count":14,"area":"lr"},{"id":"2505.10937","title":"Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2508.14313","title":"AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning","created":"2025-08-19","cited_by_count":14,"area":"lr"},{"id":"2506.04894","title":"ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests","created":"2025-06-05","cited_by_count":13,"area":"lr"},{"id":"2510.18924","title":"Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients","created":"2025-10-21","cited_by_count":13,"area":"lr"},{"id":"2406.20060","title":"Applying RLAIF for Code Generation with API-usage in Lightweight LLMs","created":"2024-06-28","cited_by_count":10,"area":"lr"},{"id":"2411.05010","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2601.22975","title":"Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2505.17652","title":"Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective","created":"2025-05-23","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":"2510.01459","title":"LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2402.09404","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability","created":"2024-02-14","cited_by_count":8,"area":"lr"},{"id":"2506.02211","title":"Improving LLM-Generated Code Quality with GRPO","created":"2025-06-02","cited_by_count":8,"area":"lr"},{"id":"2605.06908","title":"Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents","created":"2026-05-07","cited_by_count":8,"area":"lr"},{"id":"2606.22830","title":"Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation","created":"2026-06-22","cited_by_count":8,"area":"lr"},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","cited_by_count":7,"area":"lr"},{"id":"2606.15576","title":"Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning","created":"2026-06-14","cited_by_count":7,"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":"2601.07320","title":"Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training","created":"2026-01-12","cited_by_count":5,"area":"lr"},{"id":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5,"area":"lr"},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2606.21090","title":"Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2502.18487","title":"AuPair: Golden Example Pairs for Code Repair","created":"2025-02-12","cited_by_count":3,"area":"lr"},{"id":"2503.12483","title":"MoT: Modularization-of-Thought Prompting for Effective Code Generation","created":"2025-03-16","cited_by_count":2,"area":"lr"},{"id":"2511.01104","title":"HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"lr"},{"id":"2512.01174","title":"DrawingBench: Evaluating Spatial Reasoning and UI Interaction Capabilities of Large Language Models through Mouse-Based Drawing Tasks","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2512.04355","title":"Counting Without Running: Evaluating LLMs' Reasoning About Code Complexity","created":"2025-12-04","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":"2603.07779","title":"Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2605.09188","title":"DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.27000","title":"Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2608.16072","title":"Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2508.03622","title":"Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework","created":"2025-08-05","cited_by_count":1,"area":"lr"},{"id":"2509.19893","title":"Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2511.19895","title":"RPM-MCTS: Knowledge-Retrieval as Process Reward Model with Monte Carlo Tree Search for Code Generation","created":"2025-11-25","cited_by_count":1,"area":"lr"},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2604.16931","title":"Playing Psychic: Using Thought Trees to Predict Reasoning Models Accuracy on Coding Tasks","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2605.11006","title":"An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning","created":"2026-05-10","cited_by_count":1,"area":"lr"},{"id":"2605.21770","title":"Manifold-Guided Attention Steering","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.21971","title":"Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2503.14838","title":"Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning","created":"2025-03-19","cited_by_count":0,"area":"lr"},{"id":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2511.11712","title":"Reasoning: From Reflection to Solution","created":"2025-11-12","cited_by_count":0,"area":"lr"},{"id":"2602.01660","title":"CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation","created":"2026-02-02","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":"2603.17815","title":"Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.18088","title":"Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.12214","title":"Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code","created":"2026-04-14","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}