{"total":44,"rows":[{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"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":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108,"area":"lr"},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101,"area":"lr"},{"id":"2412.16075","title":"Formal Mathematical Reasoning: A New Frontier in AI","created":"2024-12-20","cited_by_count":81,"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":"2408.16293","title":"Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems","created":"2024-08-29","cited_by_count":50,"area":"lr"},{"id":"2411.13504","title":"Disentangling Memory and Reasoning Ability in Large Language Models","created":"2024-11-20","cited_by_count":44,"area":"lr"},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40,"area":"lr"},{"id":"2406.03445","title":"Pre-trained Large Language Models Use Fourier Features to Compute Addition","created":"2024-06-05","cited_by_count":39,"area":"lr"},{"id":"2604.07822","title":"Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers","created":"2026-04-09","cited_by_count":37,"area":"lr"},{"id":"2409.12568","title":"InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning","created":"2024-09-19","cited_by_count":36,"area":"lr"},{"id":"2410.19730","title":"Counting Ability of Large Language Models and Impact of Tokenization","created":"2024-10-25","cited_by_count":32,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2502.13913","title":"How Do LLMs Perform Two-Hop Reasoning in Context?","created":"2025-02-19","cited_by_count":20,"area":"lr"},{"id":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"area":"lr"},{"id":"2508.05612","title":"Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle","created":"2025-08-07","cited_by_count":19,"area":"lr"},{"id":"2505.07859","title":"Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective","created":"2025-05-08","cited_by_count":17,"area":"lr"},{"id":"2409.09239","title":"Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer","created":"2024-09-14","cited_by_count":16,"area":"lr"},{"id":"2507.11662","title":"Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification","created":"2025-07-15","cited_by_count":14,"area":"lr"},{"id":"2501.14002","title":"Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages","created":"2025-01-23","cited_by_count":13,"area":"lr"},{"id":"2502.20592","title":"Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","cited_by_count":11,"area":"lr"},{"id":"2505.14178","title":"Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2507.10624","title":"Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning","created":"2025-07-14","cited_by_count":9,"area":"lr"},{"id":"2409.14759","title":"VLM's Eye Examination: Instruct and Inspect Visual Competency of Vision Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2409.10840","title":"Implicit Reasoning in Deep Time Series Forecasting","created":"2024-09-17","cited_by_count":5,"area":"lr"},{"id":"2410.14198","title":"Supervised Chain of Thought","created":"2024-10-18","cited_by_count":5,"area":"lr"},{"id":"2505.20993","title":"Who Reasons in the Large Language Models?","created":"2025-05-27","cited_by_count":5,"area":"lr"},{"id":"2506.02591","title":"On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures","created":"2025-06-03","cited_by_count":5,"area":"lr"},{"id":"2507.04782","title":"Reason to Rote: Rethinking Memorization in Reasoning","created":"2025-07-07","cited_by_count":5,"area":"lr"},{"id":"2510.12157","title":"Self-Verifying Reflection Helps Transformers with CoT Reasoning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2502.06037","title":"Investigating Compositional Reasoning in Time Series Foundation Models","created":"2025-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.20969","title":"Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge","created":"2026-03-21","cited_by_count":3,"area":"lr"},{"id":"2503.10408","title":"Out-of-Context Reasoning in Large Language Models","created":"2025-03-13","cited_by_count":2,"area":"lr"},{"id":"2502.18435","title":"What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2507.11954","title":"The benefits of query-based KGQA systems for complex and temporal questions in LLM era","created":"2025-07-16","cited_by_count":1,"area":"lr"},{"id":"2511.07457","title":"GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2605.26789","title":"Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2502.19907","title":"Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation","created":"2025-02-27","cited_by_count":0,"area":"lr"},{"id":"2505.12896","title":"On the Thinking-Language Modeling Gap in Large Language Models","created":"2025-05-19","cited_by_count":0,"area":"lr"},{"id":"2604.01430","title":"Improving Latent Generalization Using Test-time Compute","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2606.09338","title":"Multi-Hop Knowledge Composition is Bound by Pretraining Exposure","created":"2026-06-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}