{"total":129,"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":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"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":"2605.13829","title":"Negation Neglect: When models fail to learn negations in training","created":"2026-05-13","cited_by_count":6,"area":null},{"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":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"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":"2605.18548","title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"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":"2604.25578","title":"Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling","created":"2026-04-28","cited_by_count":3,"area":"moe"},{"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":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"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":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"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":"2606.28551","title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"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":"2604.14463","title":"Psychological Steering of Large Language Models","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.16197","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","created":"2026-04-17","cited_by_count":1,"area":null},{"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":"2604.25872","title":"When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient","created":"2026-04-28","cited_by_count":1,"area":"alignment"},{"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":"2605.18607","title":"Forecasting Downstream Performance of LLMs With Proxy Metrics","created":"2026-05-18","cited_by_count":1,"area":null},{"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":"2606.12764","title":"Detecting Functional Memorization in Code Language Models","created":"2026-06-11","cited_by_count":1,"area":null},{"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":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.09424","title":"A Sovereign, Open-Source Foundation Model for German and English","created":"2026-07-10","cited_by_count":1,"area":"moe"},{"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":"2608.05224","title":"Small Foundation Models of Human Cognition and Behaviour","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.07594","title":"Scaling Inherently Interpretable Language Models","created":"2026-08-06","cited_by_count":1,"area":"diffusion"},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"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":"2609.32610","title":"KV-Lingo: Learning KV-Cache Translators with Distillation","created":"2026-09-26","cited_by_count":1,"area":"inference"},{"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":"2603.27164","title":"daVinci-LLM:Towards the Science of Pretraining","created":"2026-03-28","cited_by_count":0,"area":null},{"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":"2605.14200","title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"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":"2605.25170","title":"Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation","created":"2026-05-24","cited_by_count":0,"area":"wm"},{"id":"2605.28020","title":"The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"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":"2606.01260","title":"IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages","created":"2026-05-31","cited_by_count":0,"area":null},{"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":"2606.06622","title":"UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs","created":"2026-06-04","cited_by_count":0,"area":null},{"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":"2608.19857","title":"Inadvertent Context Leakage in Language Models","created":"2026-08-20","cited_by_count":0,"area":null},{"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"}],"next_cursor":"100"}