{"total":86,"rows":[{"id":"2607.05184","title":"Rethinking On-Policy Self-Distillation for Thinking Models","created":"2026-07-06","cited_by_count":39,"area":"lr"},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"area":"lr"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2605.11609","title":"Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information","created":"2026-05-12","cited_by_count":14,"area":"lr"},{"id":"2604.04917","title":"Vero: An Open RL Recipe for General Visual Reasoning","created":"2026-04-06","cited_by_count":11,"area":"lr"},{"id":"2602.11149","title":"Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning","created":"2026-02-11","cited_by_count":8,"area":"lr"},{"id":"2603.21177","title":"Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts","created":"2026-03-22","cited_by_count":8,"area":"lr"},{"id":"2604.22709","title":"Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought","created":"2026-04-24","cited_by_count":8,"area":"lr"},{"id":"2601.03154","title":"Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2601.07153","title":"Can Large Language Models Understand, Reason About, and Generate Code-Switched Text?","created":"2026-01-12","cited_by_count":5,"area":"lr"},{"id":"2602.02581","title":"QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals","created":"2026-01-31","cited_by_count":5,"area":"lr"},{"id":"2603.20508","title":"Measuring Weak-to-Strong Legibility of Reasoning Models","created":"2026-03-20","cited_by_count":5,"area":"lr"},{"id":"2604.04443","title":"DeonticBench: A Benchmark for Reasoning over Rules","created":"2026-04-06","cited_by_count":5,"area":"lr"},{"id":"2604.12378","title":"ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance","created":"2026-04-14","cited_by_count":5,"area":"lr"},{"id":"2606.05402","title":"ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces","created":"2026-06-03","cited_by_count":5,"area":"lr"},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2602.01600","title":"Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2603.18325","title":"Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum","created":"2026-03-18","cited_by_count":4,"area":"lr"},{"id":"2603.20172","title":"Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation","created":"2026-03-20","cited_by_count":4,"area":"lr"},{"id":"2605.12519","title":"Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2605.25507","title":"Credit Assignment with Resets in Language Model Reasoning","created":"2026-05-25","cited_by_count":4,"area":"lr"},{"id":"2601.20829","title":"Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2602.08658","title":"Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.17070","title":"Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2604.06192","title":"The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2604.07269","title":"Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent","created":"2026-04-08","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":"2606.25013","title":"Do Thinking Tokens Help with Safety?","created":"2026-06-23","cited_by_count":3,"area":"lr"},{"id":"2601.21000","title":"UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop","created":"2026-01-28","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":"2603.02208","title":"Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2603.05099","title":"ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGI","created":"2026-03-05","cited_by_count":2,"area":"lr"},{"id":"2603.09957","title":"Think Before You Lie: How Reasoning Leads to Honesty","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2605.10805","title":"Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2605.26735","title":"Rethinking the Multilingual Reasoning Gap with Layer Swap","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2605.27765","title":"Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2606.16140","title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2606.29985","title":"Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2604.09494","title":"RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2604.21454","title":"Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2604.27251","title":"Compliance vs. Sensibility: On the Reasoning Controllability in Large Language Models","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2605.07307","title":"Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.07315","title":"LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.28913","title":"Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2606.19697","title":"Efficiently Representing Algorithms With Chain-of-Thought Transformers","created":"2026-06-18","cited_by_count":1,"area":"lr"},{"id":"2607.00482","title":"Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2607.27631","title":"ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2607.27919","title":"Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2608.18931","title":"Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck","created":"2026-08-19","cited_by_count":1,"area":"lr"},{"id":"2608.29464","title":"Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered","created":"2026-08-29","cited_by_count":1,"area":"lr"},{"id":"2603.17333","title":"Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.10827","title":"Know Thy Reasoner: Not All Language Models Explore Alike","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2604.19295","title":"TEMPO: Scaling Test-time Training for Large Reasoning Models","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2604.26173","title":"Entropy Centroids as Intrinsic Rewards for Test-Time Scaling","created":"2026-04-28","cited_by_count":0,"area":"lr"},{"id":"2605.20201","title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2605.24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2605.24873","title":"Towards a Universal Causal Reasoner","created":"2026-05-24","cited_by_count":0,"area":"lr"},{"id":"2605.29190","title":"When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.03057","title":"Rethinking Molecular Text Representations for LLMs: An Empirical Study","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.03817","title":"Rethinking the Idiomaticity Decomposability Hypothesis: Evidence from Distributional Learning","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.09052","title":"INFUSER: Influence-Guided Self-Evolution Improves Reasoning","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2606.15884","title":"Neuron Level Analysis of Large Language Model in Legal Domain Reasoning","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2606.16934","title":"Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2607.20448","title":"Domyn-Small: A European 10B Reasoning Language Model","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2608.08447","title":"Hidden Language Consistency Phenomena in Reasoning LLMs","created":"2026-08-09","cited_by_count":0,"area":"lr"},{"id":"2608.22854","title":"Thinking at the Right Size: Amortized Distillation Across Post-Trained LLMs","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2608.28600","title":"SHAPE of Chain-of-Thought in Math Reasoning","created":"2026-06-28","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":"2609.10445","title":"Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.14708","title":"Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.19465","title":"Compositional Reasoning in Language Models under Reinforcement Learning Post-Training","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.19671","title":"When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.26704","title":"Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.32035","title":"Reasoning Concentrates Errors, and Self-Consistency Never Notices","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.33851","title":"Rethinking Contextualization by Reinterpreting Attention Head Channels","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35312","title":"MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35426","title":"Frontier Learning: Training LLM Reasoners at the Edge of Capability","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.39118","title":"Diagnosing On-Policy Self-Distillation for Reasoning Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39846","title":"When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.00724","title":"Reason in Style: Discovering and Controlling Style in Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.06851","title":"Base Models Can Reason By Taking a Cue From Training Data","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.07894","title":"Rethinking Faithfulness in LLMs: A Pairwise Context-Sensitive Perspective","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.09541","title":"Certified by Abstention: Distribution-Free Guarantees for Chain-of-Thought Verifiers at Small Calibration Budgets","created":"2026-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}