{"total":73,"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":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304,"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":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165,"area":"lr"},{"id":"2505.00949","title":"Llama-Nemotron: Efficient Reasoning Models","created":"2025-05-02","cited_by_count":158,"area":"lr"},{"id":"2502.07374","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!","created":"2025-02-11","cited_by_count":132,"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":"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":"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":"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":"2410.04707","title":"Learning How Hard to Think: Input-Adaptive Allocation of LM Computation","created":"2024-10-07","cited_by_count":70,"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":"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":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"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":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"area":"lr"},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","created":"2025-08-11","cited_by_count":39,"area":"lr"},{"id":"2505.24183","title":"QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation","created":"2025-05-30","cited_by_count":35,"area":"lr"},{"id":"2505.05315","title":"Scalable Chain of Thoughts via Elastic Reasoning","created":"2025-05-08","cited_by_count":34,"area":"lr"},{"id":"2501.01054","title":"Dynamic Scaling of Unit Tests for Code Reward Modeling","created":"2025-01-02","cited_by_count":33,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"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":"2507.09075","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","created":"2025-07-11","cited_by_count":25,"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":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"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":"2412.18279","title":"Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization","created":"2024-12-24","cited_by_count":17,"area":"lr"},{"id":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"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":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","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":"2602.14338","title":"Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning","created":"2026-02-15","cited_by_count":14,"area":"lr"},{"id":"2504.11919","title":"Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading","created":"2025-04-16","cited_by_count":11,"area":"lr"},{"id":"2508.21107","title":"Learning to Generate Unit Test via Adversarial Reinforcement Learning","created":"2025-08-28","cited_by_count":11,"area":"lr"},{"id":"2506.14731","title":"Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs","created":"2025-06-17","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":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","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":"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":"2506.00027","title":"From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling","created":"2025-05-24","cited_by_count":5,"area":"lr"},{"id":"2606.08446","title":"Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models","created":"2026-06-07","cited_by_count":5,"area":"lr"},{"id":"2509.25810","title":"Learning to Reason as Action Abstractions with Scalable Mid-Training RL","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2510.06101","title":"The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models","created":"2025-10-07","cited_by_count":2,"area":"lr"},{"id":"2601.17593","title":"From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMs","created":"2026-01-24","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":"2605.18871","title":"Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning","created":"2026-05-15","cited_by_count":2,"area":"lr"},{"id":"2606.07950","title":"The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning","created":"2026-06-06","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":"2509.19681","title":"Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving","created":"2025-09-24","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":"2511.04439","title":"CoRPO: Adding a Correctness Bias to GRPO Improves Generalization","created":"2025-11-06","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":"2607.19962","title":"EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization","created":"2026-07-22","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":"2510.17598","title":"Reasoning Distillation and Structural Alignment for Improved Code Generation","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2609.33570","title":"HiLoRe: What to Store, Compress, or Recompute for Efficient GRPO Training","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34359","title":"Improving Large Language Models for Code through Runtime Program-State Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.04596","title":"DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.14572","title":"Reward-Aligned Distillation","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}