{"total":109,"rows":[{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341,"area":"lr"},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498,"area":"lr"},{"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":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377,"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":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2502.18581","title":"Scalable Best-of-N Selection for Large Language Models via Self-Certainty","created":"2025-02-25","cited_by_count":187,"area":"lr"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123,"area":"lr"},{"id":"2502.18080","title":"Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning","created":"2025-02-25","cited_by_count":119,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109,"area":"lr"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2503.08569","title":"DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process","created":"2025-03-11","cited_by_count":100,"area":"lr"},{"id":"2504.07128","title":"DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning","created":"2025-04-02","cited_by_count":92,"area":"lr"},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2505.16552","title":"Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains","created":"2025-05-22","cited_by_count":85,"area":"lr"},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84,"area":"lr"},{"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":"2503.01067","title":"All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning","created":"2025-03-03","cited_by_count":59,"area":"alignment"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2506.05256","title":"Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning","created":"2025-06-05","cited_by_count":52,"area":"lr"},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2504.11543","title":"REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites","created":"2025-04-15","cited_by_count":45,"area":"agents"},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37,"area":"lr"},{"id":"2504.04383","title":"Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning","created":"2025-04-06","cited_by_count":34,"area":"lr"},{"id":"2502.07202","title":"Monte Carlo Tree Diffusion for System 2 Planning","created":"2025-02-11","cited_by_count":33,"area":"lr"},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"area":"lr"},{"id":"2503.19618","title":"Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data","created":"2025-03-25","cited_by_count":29,"area":null},{"id":"2506.05744","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","created":"2025-06-06","cited_by_count":29,"area":"lr"},{"id":"2505.13438","title":"Optimizing Anytime Reasoning via Budget Relative Policy Optimization","created":"2025-05-19","cited_by_count":27,"area":"lr"},{"id":"2502.01694","title":"Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation","created":"2025-02-02","cited_by_count":25,"area":"lr"},{"id":"2502.06773","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2601.14750","title":"Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning","created":"2026-01-21","cited_by_count":20,"area":"lr"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2506.06923","title":"Boosting LLM Reasoning via Spontaneous Self-Correction","created":"2025-06-07","cited_by_count":18,"area":"lr"},{"id":"2506.09853","title":"Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning","created":"2025-06-11","cited_by_count":17,"area":"lr"},{"id":"2502.15969","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","created":"2025-02-21","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2506.12860","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","created":"2025-06-15","cited_by_count":15,"area":"lr"},{"id":"2504.03930","title":"Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transition","created":"2025-04-04","cited_by_count":14,"area":"lr"},{"id":"2505.14216","title":"Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning","created":"2025-05-20","cited_by_count":14,"area":"lr"},{"id":"2505.21825","title":"Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2507.00417","title":"ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context","created":"2025-07-01","cited_by_count":13,"area":"lr"},{"id":"2508.12211","title":"Improving Pre-Trained Vision-Language-Action Policies with Model-Based Search","created":"2025-08-17","cited_by_count":13,"area":"vla"},{"id":"2505.20223","title":"Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects","created":"2025-05-26","cited_by_count":12,"area":"lr"},{"id":"2502.11514","title":"Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study","created":"2025-02-17","cited_by_count":11,"area":"lr"},{"id":"2505.21765","title":"Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models","created":"2025-05-27","cited_by_count":11,"area":"lr"},{"id":"2506.07712","title":"Through the Valley: Path to Effective Long CoT Training for Small Language Models","created":"2025-06-09","cited_by_count":11,"area":"lr"},{"id":"2503.13356","title":"Agents Play Thousands of 3D Video Games","created":"2025-03-17","cited_by_count":9,"area":"agents"},{"id":"2505.20561","title":"Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2506.10054","title":"Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs","created":"2025-06-11","cited_by_count":9,"area":"alignment"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2510.07312","title":"h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning","created":"2025-10-08","cited_by_count":9,"area":"lr"},{"id":"2603.15617","title":"Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification","created":"2026-03-16","cited_by_count":9,"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":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","cited_by_count":8,"area":"lr"},{"id":"2503.17885","title":"Reasoning with LLMs for Zero-Shot Vulnerability Detection","created":"2025-03-22","cited_by_count":7,"area":"lr"},{"id":"2505.14212","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2505.19949","title":"Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2506.00309","title":"Evaluation of LLMs for mathematical problem solving","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2502.18239","title":"Unveiling and Causalizing CoT: A Causal Pespective","created":"2025-02-25","cited_by_count":6,"area":"lr"},{"id":"2506.09498","title":"Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning","created":"2025-06-11","cited_by_count":6,"area":"diffusion"},{"id":"2509.00544","title":"When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment","created":"2025-08-30","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2503.08193","title":"Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents","created":"2025-03-11","cited_by_count":5,"area":"lr"},{"id":"2503.13661","title":"Pensez: Less Data, Better Reasoning -- Rethinking French LLM","created":"2025-03-17","cited_by_count":5,"area":"lr"},{"id":"2508.18812","title":"STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning","created":"2025-08-26","cited_by_count":5,"area":"lr"},{"id":"2505.13718","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2508.20018","title":"SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2509.20186","title":"Thinking Augmented Pre-training","created":"2025-09-24","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":"2504.16414","title":"Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study","created":"2025-04-23","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":"2510.04116","title":"Searching Meta Reasoning Skeleton to Guide LLM Reasoning","created":"2025-10-05","cited_by_count":3,"area":"lr"},{"id":"2510.11121","title":"Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2505.12500","title":"MARGE: Improving Math Reasoning for LLMs with Guided Exploration","created":"2025-05-18","cited_by_count":2,"area":"lr"},{"id":"2506.10161","title":"Can LLMs Generate Good Stories? Insights and Challenges from a Narrative Planning Perspective","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2602.01709","title":"ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2605.25745","title":"Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2504.02404","title":"AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs","created":"2025-04-03","cited_by_count":1,"area":"lr"},{"id":"2505.12031","title":"LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation","created":"2025-05-17","cited_by_count":1,"area":"synth"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2508.01763","title":"Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2512.20586","title":"Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent","created":"2025-12-23","cited_by_count":1,"area":"lr"},{"id":"2601.03769","title":"EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2602.01695","title":"Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.10494","title":"Canvas-of-Thought: Grounding Reasoning via Mutable Structured States","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2604.12816","title":"The role of System 1 and System 2 semantic memory structure in human and LLM biases","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2606.02871","title":"Adaptive Latent Agentic Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.03965","title":"Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.05736","title":"VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2606.14674","title":"AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition","created":"2026-06-12","cited_by_count":1,"area":"agents"},{"id":"2503.01066","title":"Alchemist: Towards the Design of Efficient Online Continual Learning System","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.17288","title":"Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2505.17829","title":"Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning","created":"2025-05-23","cited_by_count":0,"area":"lr"},{"id":"2507.08501","title":"From Language to Logic: A Bi-Level Framework for Structured Reasoning","created":"2025-07-11","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}