{"total":33,"rows":[{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2508.08636","title":"InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling","created":"2025-08-12","cited_by_count":20,"area":"lr"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2506.15787","title":"SLR: Automated Synthesis for Scalable Logical Reasoning","created":"2025-06-18","cited_by_count":6,"area":"lr"},{"id":"2509.04059","title":"Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning","created":"2025-09-04","cited_by_count":6,"area":"lr"},{"id":"2601.22642","title":"Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.20117","title":"ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Models","created":"2026-02-23","cited_by_count":5,"area":"lr"},{"id":"2507.09751","title":"Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations","created":"2025-07-13","cited_by_count":4,"area":"lr"},{"id":"2512.16144","title":"INTELLECT-3: Technical Report","created":"2025-12-18","cited_by_count":4,"area":"lr"},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2606.01599","title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2603.02208","title":"Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2601.03205","title":"UltraLogic: Enhancing LLM Reasoning through Large-Scale Data Synthesis and Bipolar Float Reward","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2601.16480","title":"TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2605.06638","title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2606.26797","title":"Reasoning Quality Emerges Early: Data Curation for Reasoning Models","created":"2026-06-25","cited_by_count":1,"area":"lr"},{"id":"2508.15180","title":"PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data","created":"2025-08-21","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","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":"2604.08477","title":"SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.26173","title":"Entropy Centroids as Intrinsic Rewards for Test-Time Scaling","created":"2026-04-28","cited_by_count":0,"area":"lr"},{"id":"2605.14215","title":"GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.25486","title":"RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2605.28421","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2608.02101","title":"Cross-Domain Hybrid OPD for Generalizable Search Agents","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2609.35426","title":"Frontier Learning: Training LLM Reasoners at the Edge of Capability","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.04882","title":"ResOPD: Tail Residualization for Sparse On-Policy Distillation","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}