{"total":113,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","created":"2026-04-14","cited_by_count":299,"area":"lr"},{"id":"2505.22648","title":"WebDancer: Towards Autonomous Information Seeking Agency","created":"2025-05-28","cited_by_count":188,"area":"agents"},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113,"area":"lr"},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2506.17211","title":"BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning","created":"2025-06-20","cited_by_count":63,"area":"lr"},{"id":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","cited_by_count":62,"area":"lr"},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58,"area":"lr"},{"id":"2504.12329","title":"Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time","created":"2025-04-12","cited_by_count":48,"area":"lr"},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2505.22334","title":"Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2506.18234","title":"Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning","created":"2025-06-23","cited_by_count":38,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2506.05744","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","created":"2025-06-06","cited_by_count":29,"area":"lr"},{"id":"2605.07804","title":"Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning","created":"2026-05-08","cited_by_count":27,"area":"lr"},{"id":"2605.10889","title":"Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why","created":"2026-05-11","cited_by_count":25,"area":"lr"},{"id":"2503.17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities","created":"2025-03-23","cited_by_count":20,"area":"lr"},{"id":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19,"area":"lr"},{"id":"2505.14582","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","created":"2025-05-20","cited_by_count":19,"area":"lr"},{"id":"2607.13399","title":"Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations","created":"2026-07-15","cited_by_count":19,"area":"distill"},{"id":"2504.15362","title":"LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception","created":"2025-04-21","cited_by_count":16,"area":"lr"},{"id":"2505.15257","title":"When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners","created":"2025-05-21","cited_by_count":16,"area":"lr"},{"id":"2603.24596","title":"X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs","created":"2026-03-06","cited_by_count":16,"area":"distill"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2510.10925","title":"Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation","created":"2025-10-13","cited_by_count":15,"area":"synth"},{"id":"2505.07961","title":"Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"id":"2506.00320","title":"Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents","created":"2025-05-31","cited_by_count":14,"area":"wm"},{"id":"2506.01748","title":"Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning","created":"2025-06-02","cited_by_count":14,"area":"lr"},{"id":"2503.01461","title":"Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models","created":"2025-03-03","cited_by_count":13,"area":"lr"},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","cited_by_count":13,"area":"lr"},{"id":"2606.30626","title":"DOPD: Dual On-policy Distillation","created":"2026-06-29","cited_by_count":12,"area":"distill"},{"id":"2506.08140","title":"AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists","created":"2025-06-09","cited_by_count":11,"area":null},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2506.08388","title":"Reinforcement Learning Teachers of Test Time Scaling","created":"2025-06-10","cited_by_count":10,"area":"lr"},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2507.01887","title":"MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants","created":"2025-07-02","cited_by_count":9,"area":"lr"},{"id":"2603.15500","title":"Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty","created":"2026-03-16","cited_by_count":9,"area":"lr"},{"id":"2510.03988","title":"The Signal is in the Steps: Local Scoring for Reasoning Data Selection","created":"2025-10-05","cited_by_count":8,"area":"distill"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2507.17075","title":"LoRA is All You Need for Safety Alignment of Reasoning LLMs","created":"2025-07-22","cited_by_count":6,"area":"lr"},{"id":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"area":"lr"},{"id":"2601.10064","title":"Long-Chain Reasoning Distillation via Adaptive Prefix Alignment","created":"2026-01-15","cited_by_count":6,"area":"lr"},{"id":"2507.18178","title":"Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory","created":"2025-07-24","cited_by_count":5,"area":"lr"},{"id":"2511.02833","title":"In Good GRACEs: Principled Teacher Selection for Knowledge Distillation","created":"2025-11-04","cited_by_count":5,"area":"distill"},{"id":"2601.04611","title":"Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2609.02998","title":"Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation","created":"2026-09-02","cited_by_count":5,"area":"distill"},{"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":"2512.00003","title":"Efficient Turing Machine Simulation with Transformers","created":"2025-09-28","cited_by_count":4,"area":"lr"},{"id":"2601.10348","title":"Training-Trajectory-Aware Token Selection","created":"2026-01-15","cited_by_count":4,"area":"lr"},{"id":"2603.03752","title":"Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning","created":"2026-03-04","cited_by_count":4,"area":"lr"},{"id":"2505.22131","title":"Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2508.16677","title":"Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration","created":"2025-08-21","cited_by_count":3,"area":"lr"},{"id":"2510.24328","title":"Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2511.00536","title":"Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly","created":"2025-11-01","cited_by_count":3,"area":"lr"},{"id":"2604.26940","title":"Select to Think: Unlocking SLM Potential with Local Sufficiency","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2606.30445","title":"When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon","created":"2026-06-29","cited_by_count":3,"area":"offlinerl"},{"id":"2506.04205","title":"EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation","created":"2025-06-04","cited_by_count":2,"area":"lr"},{"id":"2511.06512","title":"EASE: Practical and Efficient Safety Alignment for Small Language Models","created":"2025-11-09","cited_by_count":2,"area":"alignment"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2503.04848","title":"Three tiers of computation in transformers and in brain architectures","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2508.10019","title":"Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2508.18743","title":"CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2509.15661","title":"SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models","created":"2025-09-19","cited_by_count":1,"area":"lr"},{"id":"2509.21170","title":"Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2602.22225","title":"SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG","created":"2025-12-17","cited_by_count":1,"area":"rag"},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2604.11290","title":"Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation","created":"2026-04-13","cited_by_count":1,"area":"synth"},{"id":"2604.21950","title":"Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.08472","title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2605.13165","title":"STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.29247","title":"DenseSteer: Steering Small Language Models towards Dense Math Reasoning","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2607.03801","title":"Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2607.16851","title":"AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM Agents","created":"2026-07-18","cited_by_count":1,"area":"agents"},{"id":"2608.13721","title":"Capacity-Dependent Effects of Data Selection for Reasoning","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2609.26216","title":"Beyond Imitation: Auditing the Recoverability of Reasoning in Distilled Models","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.37326","title":"Solving Without Stopping: On-Policy Distillation at Small Scale","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2505.14852","title":"EasyMath: A 0-shot Math Benchmark for SLMs","created":"2025-05-20","cited_by_count":0,"area":"lr"},{"id":"2508.05234","title":"Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation","created":"2025-08-07","cited_by_count":0,"area":"lr"},{"id":"2602.18749","title":"Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocation","created":"2026-02-21","cited_by_count":0,"area":"lr"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2604.01652","title":"ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.05114","title":"$\\pi^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.06205","title":"Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation","created":"2026-03-15","cited_by_count":0,"area":"lr"},{"id":"2604.12748","title":"Generating Effective CoT Traces for Mitigating Causal Hallucination","created":"2026-04-14","cited_by_count":0,"area":"lr"},{"id":"2604.23809","title":"LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models","created":"2026-04-26","cited_by_count":0,"area":"lr"},{"id":"2605.02290","title":"Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding","created":"2026-05-04","cited_by_count":0,"area":"lr"},{"id":"2605.28888","title":"Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.04466","title":"Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoning","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.16152","title":"The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.24747","title":"Scaling Laws for Task-Specific LLM Distillation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.28166","title":"Tandem Reinforcement Learning with Verifiable Rewards","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.18034","title":"AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":"100"}