{"total":79,"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":"2502.01100","title":"ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning","created":"2025-02-03","cited_by_count":201,"area":"lr"},{"id":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"area":"lr"},{"id":"2505.16400","title":"AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning","created":"2025-05-22","cited_by_count":87,"area":"lr"},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2504.02956","title":"Understanding Aha Moments: from External Observations to Internal Mechanisms","created":"2025-04-03","cited_by_count":50,"area":"lr"},{"id":"2505.19641","title":"SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond","created":"2025-05-26","cited_by_count":50,"area":"lr"},{"id":"2504.09710","title":"DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training","created":"2025-04-13","cited_by_count":46,"area":"lr"},{"id":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"2602.22495","title":"Reinforcement-aware Knowledge Distillation for LLM Reasoning","created":"2026-02-26","cited_by_count":35,"area":"lr"},{"id":"2510.01367","title":"Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort","created":"2025-10-01","cited_by_count":27,"area":"lr"},{"id":"2505.12284","title":"Shorten After You're Right: Lazy Length Penalties for Reasoning RL","created":"2025-05-18","cited_by_count":25,"area":"lr"},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21,"area":"lr"},{"id":"2505.14815","title":"Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21,"area":"lr"},{"id":"2507.04766","title":"ABench-Physics: Benchmarking Physical Reasoning in LLMs via High-Difficulty and Dynamic Physics Problems","created":"2025-07-07","cited_by_count":18,"area":"lr"},{"id":"2506.04810","title":"Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study","created":"2025-06-05","cited_by_count":17,"area":"lr"},{"id":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2604.06628","title":"Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability","created":"2026-04-08","cited_by_count":14,"area":"lr"},{"id":"2412.14368","title":"Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs","created":"2024-12-18","cited_by_count":12,"area":"lr"},{"id":"2504.04524","title":"Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning","created":"2025-04-06","cited_by_count":12,"area":"lr"},{"id":"2509.00084","title":"Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs","created":"2025-08-27","cited_by_count":12,"area":"lr"},{"id":"2506.22950","title":"Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models","created":"2025-06-28","cited_by_count":10,"area":"lr"},{"id":"2506.15211","title":"ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs","created":"2025-06-18","cited_by_count":9,"area":"lr"},{"id":"2603.02203","title":"Tool Verification for Test-Time Reinforcement Learning","created":"2026-03-02","cited_by_count":9,"area":"lr"},{"id":"2505.12717","title":"ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving","created":"2025-05-19","cited_by_count":8,"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":"2505.20630","title":"SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"id":"2509.23129","title":"C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning","created":"2025-09-27","cited_by_count":8,"area":"lr"},{"id":"2510.00237","title":"Debunk the Myth of SFT Generalization","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2503.19599","title":"HoarePrompt: Structural Reasoning About Program Correctness in Natural Language","created":"2025-03-25","cited_by_count":7,"area":"lr"},{"id":"2506.18485","title":"A Simple \"Motivation\" Can Enhance Reinforcement Finetuning of Large Reasoning Models","created":"2025-06-23","cited_by_count":7,"area":"lr"},{"id":"2506.15787","title":"SLR: Automated Synthesis for Scalable Logical Reasoning","created":"2025-06-18","cited_by_count":6,"area":"lr"},{"id":"2507.00951","title":"Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact","created":"2025-07-01","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":"2603.23414","title":"SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling","created":"2026-03-24","cited_by_count":6,"area":"lr"},{"id":"2503.23913","title":"Entropy-Based Adaptive Weighting for Self-Training","created":"2025-03-31","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":"2510.18184","title":"ActivationReasoning: Logical Reasoning in Latent Activation Spaces","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2601.22642","title":"Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","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":"2508.02037","title":"Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time","created":"2025-08-04","cited_by_count":4,"area":"lr"},{"id":"2508.05015","title":"SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2510.07169","title":"More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2511.00066","title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"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":"2606.01075","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","created":"2026-05-31","cited_by_count":4,"area":"lr"},{"id":"2505.17988","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","created":"2025-05-23","cited_by_count":3,"area":"lr"},{"id":"2505.22318","title":"Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds","created":"2025-05-28","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":"2603.29500","title":"Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries","created":"2026-03-31","cited_by_count":3,"area":"lr"},{"id":"2605.18864","title":"SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs","created":"2026-05-15","cited_by_count":3,"area":"lr"},{"id":"2509.01619","title":"Throttling Web Agents Using Reasoning Gates","created":"2025-09-01","cited_by_count":2,"area":"lr"},{"id":"2605.07053","title":"GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2502.12821","title":"Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2505.12951","title":"DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management","created":"2025-05-19","cited_by_count":1,"area":"lr"},{"id":"2507.14393","title":"Adaptive Multi-Agent Reasoning via Automated Workflow Generation","created":"2025-07-18","cited_by_count":1,"area":"lr"},{"id":"2510.21853","title":"Policy Optimization Prefers The Path of Least Resistance","created":"2025-10-22","cited_by_count":1,"area":"lr"},{"id":"2511.06160","title":"Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles","created":"2025-11-08","cited_by_count":1,"area":"lr"},{"id":"2601.16823","title":"Disentangling generalization and memorization in large language models using chess","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2603.26323","title":"From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs","created":"2026-03-27","cited_by_count":1,"area":"lr"},{"id":"2506.17630","title":"Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs","created":"2025-06-21","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"},{"id":"2509.23330","title":"Structured In-context Environment Scaling for Large Language Model Reasoning","created":"2025-09-27","cited_by_count":0,"area":"lr"},{"id":"2512.00552","title":"Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity","created":"2025-11-29","cited_by_count":0,"area":"lr"},{"id":"2512.10561","title":"Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Models","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2603.27226","title":"Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning","created":"2026-03-28","cited_by_count":0,"area":"lr"},{"id":"2605.06755","title":"Gradient Extrapolation-Based Policy Optimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.12918","title":"CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2606.24965","title":"Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners","created":"2026-06-23","cited_by_count":0,"area":"lr"},{"id":"2609.34660","title":"Rewarding Novel Deductions: Solver-guided Process Supervision for Logical Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.38409","title":"ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00991","title":"Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}