{"total":96,"rows":[{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344,"area":"lr"},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295,"area":"lr"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2405.00332","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","created":"2024-05-01","cited_by_count":191,"area":"lr"},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"area":"lr"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2407.20311","title":"Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process","created":"2024-07-29","cited_by_count":108,"area":"lr"},{"id":"2409.05556","title":"SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning","created":"2024-09-09","cited_by_count":94,"area":"lr"},{"id":"2411.16489","title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","created":"2024-11-25","cited_by_count":92,"area":"lr"},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70,"area":"lr"},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2507.16812","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning","created":"2025-07-22","cited_by_count":59,"area":"lr"},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58,"area":"lr"},{"id":"2403.02333","title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","created":"2024-03-04","cited_by_count":58,"area":"lr"},{"id":"2312.17080","title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","created":"2023-12-28","cited_by_count":57,"area":"lr"},{"id":"2504.02807","title":"MegaMath: Pushing the Limits of Open Math Corpora","created":"2025-04-03","cited_by_count":51,"area":"lr"},{"id":"2406.01940","title":"Process-Driven Autoformalization in Lean 4","created":"2024-06-04","cited_by_count":45,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2505.10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","created":"2025-05-15","cited_by_count":45,"area":"lr"},{"id":"2411.12580","title":"Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models","created":"2024-11-19","cited_by_count":41,"area":"lr"},{"id":"2505.11404","title":"Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner","created":"2025-05-16","cited_by_count":40,"area":"lr"},{"id":"2505.20161","title":"Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2410.08196","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","created":"2024-10-10","cited_by_count":39,"area":"lr"},{"id":"2402.02805","title":"Graph-enhanced Large Language Models in Asynchronous Plan Reasoning","created":"2024-02-05","cited_by_count":37,"area":"lr"},{"id":"2407.21009","title":"AI-Assisted Generation of Difficult Math Questions","created":"2024-07-30","cited_by_count":37,"area":"lr"},{"id":"2501.06458","title":"O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning","created":"2025-01-11","cited_by_count":35,"area":"lr"},{"id":"2411.04329","title":"CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models","created":"2024-11-07","cited_by_count":34,"area":"lr"},{"id":"2506.09014","title":"Learning to Reason Across Parallel Samples for LLM Reasoning","created":"2025-06-10","cited_by_count":32,"area":"lr"},{"id":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31,"area":"lr"},{"id":"2410.18798","title":"Distill Visual Chart Reasoning Ability from LLMs to MLLMs","created":"2024-10-24","cited_by_count":31,"area":"lr"},{"id":"2405.16802","title":"AutoPSV: Automated Process-Supervised Verifier","created":"2024-05-27","cited_by_count":30,"area":"lr"},{"id":"2406.13975","title":"MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2406.01006","title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","created":"2024-06-03","cited_by_count":27,"area":"lr"},{"id":"2503.08540","title":"Mellow: a small audio language model for reasoning","created":"2025-03-11","cited_by_count":27,"area":"lr"},{"id":"2407.08348","title":"Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On","created":"2024-07-11","cited_by_count":24,"area":"lr"},{"id":"2410.11005","title":"Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks","created":"2024-10-14","cited_by_count":22,"area":"lr"},{"id":"2504.20648","title":"SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data","created":"2025-04-29","cited_by_count":21,"area":"lr"},{"id":"2401.10065","title":"Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs","created":"2024-01-18","cited_by_count":20,"area":"lr"},{"id":"2410.07507","title":"Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs)","created":"2024-10-10","cited_by_count":18,"area":"lr"},{"id":"2403.19094","title":"Learning From Correctness Without Prompting Makes LLM Efficient Reasoner","created":"2024-03-28","cited_by_count":15,"area":"lr"},{"id":"2511.07378","title":"Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization","created":"2025-11-10","cited_by_count":14,"area":"lr"},{"id":"2503.21729","title":"ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation","created":"2025-03-27","cited_by_count":13,"area":"lr"},{"id":"2512.09619","title":"GLaD: Geometric Latent Distillation for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":11,"area":"lr"},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2312.15960","title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","created":"2023-12-26","cited_by_count":9,"area":"lr"},{"id":"2406.12572","title":"Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models","created":"2024-06-18","cited_by_count":8,"area":"lr"},{"id":"2508.15202","title":"Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models","created":"2025-08-21","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2410.01044","title":"RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoning","created":"2024-10-01","cited_by_count":6,"area":"lr"},{"id":"2405.03821","title":"Thoughtful Things: Building Human-Centric Smart Devices with Small Language Models","created":"2024-05-06","cited_by_count":4,"area":"lr"},{"id":"2508.05305","title":"SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens","created":"2025-08-07","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":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2510.23629","title":"Chain of Execution Supervision Promotes General Reasoning in Large Language Models","created":"2025-10-24","cited_by_count":4,"area":"lr"},{"id":"2510.25804","title":"Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2601.05073","title":"Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2602.09574","title":"Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2412.08347","title":"SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs","created":"2024-12-11","cited_by_count":3,"area":"lr"},{"id":"2504.20946","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","created":"2025-04-29","cited_by_count":3,"area":"lr"},{"id":"2505.23667","title":"Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2508.01977","title":"TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models","created":"2025-08-04","cited_by_count":3,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2512.21722","title":"MAction-SocialNav: Multi-Action Socially Compliant Navigation via Reasoning-enhanced Prompt Tuning","created":"2025-12-25","cited_by_count":3,"area":"lr"},{"id":"2602.00376","title":"MATRIX: A Multimodal Benchmark and Post-Training Framework for Materials Science","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2508.04199","title":"Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts","created":"2025-08-06","cited_by_count":2,"area":"lr"},{"id":"2510.00880","title":"HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation","created":"2025-10-01","cited_by_count":2,"area":"lr"},{"id":"2511.11810","title":"On the Notion that Language Models Reason","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2511.15958","title":"JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation","created":"2025-11-20","cited_by_count":2,"area":"lr"},{"id":"2603.04663","title":"Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector","created":"2026-03-04","cited_by_count":2,"area":"lr"},{"id":"2608.06741","title":"Solver-Guided Reasoning for Mixed-Equilibrium Strategies","created":"2026-08-07","cited_by_count":2,"area":"lr"},{"id":"2404.01084","title":"AILS-NTUA at SemEval-2024 Task 9: Cracking Brain Teasers: Transformer Models for Lateral Thinking Puzzles","created":"2024-04-01","cited_by_count":1,"area":"lr"},{"id":"2409.09613","title":"Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora","created":"2024-09-15","cited_by_count":1,"area":"lr"},{"id":"2503.05846","title":"EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context","created":"2025-03-07","cited_by_count":1,"area":"lr"},{"id":"2507.17168","title":"Improving LLMs' Generalized Reasoning Abilities by Graph Problems","created":"2025-07-23","cited_by_count":1,"area":"lr"},{"id":"2510.18909","title":"Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2604.16862","title":"Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.18936","title":"Fine-Tuning Small Reasoning Models for Quantum Field Theory","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2605.28919","title":"CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2404.13065","title":"Intellecta Cognitiva: A Comprehensive Dataset for Advancing Academic Knowledge and Machine Reasoning","created":"2024-04-13","cited_by_count":0,"area":"lr"},{"id":"2410.07062","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","created":"2024-10-09","cited_by_count":0,"area":"lr"},{"id":"2510.05133","title":"Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios","created":"2025-10-01","cited_by_count":0,"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":"2512.14427","title":"Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models","created":"2025-12-16","cited_by_count":0,"area":"lr"},{"id":"2512.23073","title":"Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models","created":"2025-12-28","cited_by_count":0,"area":"lr"},{"id":"2601.03268","title":"WRAVAL -- WRiting Assist eVALuation","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2601.14053","title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2602.03181","title":"Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2604.06298","title":"Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2604.20904","title":"Reinforcing privacy reasoning in LLMs via normative simulacra from fiction","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2606.05106","title":"Arithmetic Pedagogy for Language Models","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2608.05151","title":"Simulator-Grounded Large Language Models for Industrial Causal Reasoning: Tool-Use, Structured Injection, and Plant-Portable Retrieval for Wastewater Treatment Decision Support","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"id":"2609.01532","title":"Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2610.13285","title":"BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}