{"total":45,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304,"area":"lr"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"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":"2509.14279","title":"Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization","created":"2025-09-16","cited_by_count":56,"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":"2505.13444","title":"ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models","created":"2025-05-19","cited_by_count":32,"area":"lr"},{"id":"2505.19702","title":"Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning","created":"2025-05-26","cited_by_count":32,"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":"2510.06672","title":"XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2506.10963","title":"MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning","created":"2025-06-12","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":"2505.14733","title":"The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute","created":"2025-05-20","cited_by_count":15,"area":"lr"},{"id":"2505.17123","title":"MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation","created":"2025-05-21","cited_by_count":15,"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":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","created":"2025-11-05","cited_by_count":13,"area":"lr"},{"id":"2507.10541","title":"REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once","created":"2025-07-14","cited_by_count":12,"area":"lr"},{"id":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","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":"2502.09183","title":"RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation","created":"2025-02-13","cited_by_count":8,"area":"lr"},{"id":"2507.21476","title":"Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench","created":"2025-07-29","cited_by_count":8,"area":"lr"},{"id":"2503.19599","title":"HoarePrompt: Structural Reasoning About Program Correctness in Natural Language","created":"2025-03-25","cited_by_count":7,"area":"lr"},{"id":"2506.15787","title":"SLR: Automated Synthesis for Scalable Logical Reasoning","created":"2025-06-18","cited_by_count":6,"area":"lr"},{"id":"2505.16686","title":"SPaRC: A Spatial Pathfinding Reasoning Challenge","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2505.19987","title":"How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation","created":"2025-05-26","cited_by_count":5,"area":"lr"},{"id":"2602.14798","title":"Overthinking Loops in Agents: A Structural Risk via MCP Tools","created":"2026-02-16","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2509.12464","title":"Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction","created":"2025-09-15","cited_by_count":4,"area":"lr"},{"id":"2510.11919","title":"LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2605.17333","title":"Leveraging Error Diversity in Group Rollouts for Reinforcement Learning","created":"2026-05-17","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":"2601.12019","title":"Acting Flatterers via LLMs Sycophancy: Combating Clickbait with LLMs Opposing-Stance Reasoning","created":"2026-01-17","cited_by_count":2,"area":"lr"},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2609.15309","title":"When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis","created":"2026-09-14","cited_by_count":2,"area":"lr"},{"id":"2506.13841","title":"LocationReasoner: Evaluating LLMs on Real-World Site Selection Reasoning","created":"2025-06-16","cited_by_count":1,"area":"lr"},{"id":"2509.03537","title":"AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models","created":"2025-08-27","cited_by_count":1,"area":"lr"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2601.17421","title":"Oops, Wait: Discourse Tokens Matter in Reasoning Model","created":"2026-01-24","cited_by_count":1,"area":"lr"},{"id":"2605.07307","title":"Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2607.22098","title":"Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2506.07064","title":"Com$^2$: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models","created":"2025-06-08","cited_by_count":0,"area":"lr"},{"id":"2605.08478","title":"When Independent Sampling Outperforms Agentic Reasoning","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2607.07748","title":"Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2608.29632","title":"InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.07103","title":"Revisiting Complete Reasoning Traces for Post-Training","created":"2026-09-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}