{"total":51,"rows":[{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345,"area":"lr"},{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165,"area":"lr"},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82,"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":"2511.08923","title":"TiDAR: Think in Diffusion, Talk in Autoregression","created":"2025-11-12","cited_by_count":37,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"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":"2509.11963","title":"ToolRM: Outcome Reward Models for Tool-Calling Large Language Models","created":"2025-09-15","cited_by_count":17,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2504.04718","title":"T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models","created":"2025-04-07","cited_by_count":13,"area":"lr"},{"id":"2504.07825","title":"Who Benchmarks the Benchmarks? Towards Comprehensive Evaluation of Commonsense Reasoning Benchmarks","created":"2025-04-10","cited_by_count":11,"area":"lr"},{"id":"2602.23225","title":"Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2505.24550","title":"A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings","created":"2025-05-30","cited_by_count":9,"area":"lr"},{"id":"2506.13331","title":"Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization","created":"2025-06-16","cited_by_count":9,"area":"lr"},{"id":"2602.20330","title":"Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking","created":"2026-02-23","cited_by_count":8,"area":"lr"},{"id":"2509.24945","title":"MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2506.09967","title":"Resa: Transparent Reasoning Models via SAEs","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","cited_by_count":6,"area":"lr"},{"id":"2502.12974","title":"Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking","created":"2025-02-18","cited_by_count":5,"area":"lr"},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2507.20984","title":"SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"id":"2509.21499","title":"On Code-Induced Reasoning in LLMs","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2510.02066","title":"Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems","created":"2025-10-02","cited_by_count":5,"area":"lr"},{"id":"2510.00219","title":"Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2601.16046","title":"DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning","created":"2026-01-22","cited_by_count":4,"area":"lr"},{"id":"2602.19548","title":"Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining","created":"2026-02-23","cited_by_count":4,"area":"lr"},{"id":"2607.00341","title":"DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning","created":"2026-07-01","cited_by_count":4,"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":"2512.23292","title":"Agentic Physical AI toward a Domain-Specific Foundation Model for Energy Systems: A Case Study on Nuclear Reactor Control","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2605.12227","title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2506.01531","title":"STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework","created":"2025-06-02","cited_by_count":2,"area":"lr"},{"id":"2507.19748","title":"JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language Models","created":"2025-07-26","cited_by_count":2,"area":"lr"},{"id":"2511.07397","title":"Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents","created":"2025-11-10","cited_by_count":2,"area":"lr"},{"id":"2603.02156","title":"How Small Can 6G Reason? Scaling Tiny-to-Small Language Models for AI-Native Networks","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2605.29327","title":"Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2508.06974","title":"Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models","created":"2025-08-09","cited_by_count":1,"area":"lr"},{"id":"2508.10995","title":"Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling","created":"2025-08-14","cited_by_count":1,"area":"lr"},{"id":"2508.18672","title":"Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2601.19447","title":"KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking","created":"2026-01-27","cited_by_count":1,"area":"lr"},{"id":"2603.01353","title":"Constructing Synthetic Instruction Datasets for Improving Reasoning in Domain-Specific LLMs: A Case Study in the Japanese Financial Domain","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2508.12198","title":"Exploring Multimodal AI Reasoning for Meteorological Forecasting from Skew-T Diagrams","created":"2025-08-17","cited_by_count":0,"area":"lr"},{"id":"2601.22889","title":"DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.16867","title":"Efficient Reasoning on the Edge","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2609.20981","title":"CaLR: Causal Latent Revision for Robust Diffusion Reasoning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.36552","title":"SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.02066","title":"External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.07730","title":"SanSi: A Looped Typed Decision Model for System 1.5 Thinking","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.16489","title":"Growing and Transferring Pathways for LLM Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}