{"total":53,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2506.17218","title":"Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens","created":"2025-06-20","cited_by_count":124,"area":"lr"},{"id":"2512.06688","title":"PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory","created":"2025-12-07","cited_by_count":88,"area":"agents"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"area":"agents"},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2505.13934","title":"RLVR-World: Training World Models with Reinforcement Learning","created":"2025-05-20","cited_by_count":40,"area":"wm"},{"id":"2505.15034","title":"RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning","created":"2025-05-21","cited_by_count":40,"area":"lr"},{"id":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2606.01779","title":"HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems","created":"2026-06-01","cited_by_count":21,"area":"agents"},{"id":"2505.23604","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","created":"2025-05-29","cited_by_count":17,"area":"lr"},{"id":"2505.19406","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","created":"2025-05-26","cited_by_count":14,"area":"lr"},{"id":"2509.03059","title":"Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers","created":"2025-09-03","cited_by_count":14,"area":"lr"},{"id":"2506.18237","title":"AdapThink: Adaptive Thinking Preferences for Reasoning Language Model","created":"2025-06-23","cited_by_count":11,"area":"lr"},{"id":"2506.08388","title":"Reinforcement Learning Teachers of Test Time Scaling","created":"2025-06-10","cited_by_count":10,"area":"lr"},{"id":"2509.16456","title":"GPO: Learning from Critical Steps to Improve LLM Reasoning","created":"2025-09-19","cited_by_count":10,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2509.22391","title":"Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents","created":"2025-09-26","cited_by_count":7,"area":"agents"},{"id":"2512.10534","title":"Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning","created":"2025-12-11","cited_by_count":7,"area":"agents"},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2509.06024","title":"Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL","created":"2025-09-07","cited_by_count":5,"area":"lr"},{"id":"2509.24238","title":"Learning to Ponder: Adaptive Reasoning in Latent Space","created":"2025-09-29","cited_by_count":5,"area":"lr"},{"id":"2505.16401","title":"Divide-Fuse-Conquer: Eliciting \"Aha Moments\" in Multi-Scenario Games","created":"2025-05-22","cited_by_count":4,"area":"lr"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2602.01070","title":"What If We Allocate Test-Time Compute Adaptively?","created":"2026-02-01","cited_by_count":4,"area":"lr"},{"id":"2602.13891","title":"GSRM: Generative Speech Reward Model for Speech RLHF","created":"2026-02-14","cited_by_count":4,"area":"alignment"},{"id":"2606.01075","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","created":"2026-05-31","cited_by_count":4,"area":"lr"},{"id":"2502.17800","title":"Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training","created":"2025-02-25","cited_by_count":3,"area":"lr"},{"id":"2507.13332","title":"The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner","created":"2025-07-17","cited_by_count":3,"area":"lr"},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2601.01392","title":"SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2603.06065","title":"ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"id":"2508.10019","title":"Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2511.06065","title":"ScRPO: From Errors to Insights","created":"2025-11-08","cited_by_count":1,"area":"lr"},{"id":"2602.19069","title":"Asking the Right Questions: Improving Reasoning with Generated Stepping Stones","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2605.07353","title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.18851","title":"STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.22138","title":"Efficient Agentic Reasoning Through Self-Regulated Simulative Planning","created":"2026-05-21","cited_by_count":1,"area":"wm"},{"id":"2608.30109","title":"COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learning","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2504.09777","title":"Reasoning without Regret","created":"2025-04-14","cited_by_count":0,"area":"lr"},{"id":"2511.20694","title":"Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning","created":"2025-11-23","cited_by_count":0,"area":"lr"},{"id":"2601.12988","title":"PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient","created":"2026-01-19","cited_by_count":0,"area":"agents"},{"id":"2604.04226","title":"SW-$A^2$-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web","created":"2026-04-05","cited_by_count":0,"area":"agents"},{"id":"2605.18261","title":"Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains","created":"2026-05-18","cited_by_count":0,"area":"lr"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.31260","title":"Plan Right, Then Plan Tight: Symbolic RL for Efficient Embodied Reasoning","created":"2026-06-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}