{"total":141,"rows":[{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883,"area":"lr"},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455,"area":"lr"},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329,"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":"2602.12125","title":"Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation","created":"2026-02-12","cited_by_count":184,"area":"lr"},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117,"area":"lr"},{"id":"2410.23875","title":"Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs","created":"2024-10-31","cited_by_count":78,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"area":"lr"},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67,"area":"lr"},{"id":"2304.04812","title":"Scallop: A Language for Neurosymbolic Programming","created":"2023-04-10","cited_by_count":63,"area":"lr"},{"id":"2303.00293","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","created":"2023-03-01","cited_by_count":58,"area":"lr"},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2506.02208","title":"KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning","created":"2025-06-02","cited_by_count":41,"area":"lr"},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36,"area":"lr"},{"id":"2305.17878","title":"Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models","created":"2023-05-29","cited_by_count":31,"area":"lr"},{"id":"2305.13888","title":"PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning","created":"2023-05-23","cited_by_count":29,"area":"lr"},{"id":"2310.14747","title":"MCC-KD: Multi-CoT Consistent Knowledge Distillation","created":"2023-10-23","cited_by_count":28,"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":"2503.07234","title":"CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting","created":"2025-03-10","cited_by_count":26,"area":"lr"},{"id":"2309.13182","title":"Effective Distillation of Table-based Reasoning Ability from LLMs","created":"2023-09-22","cited_by_count":23,"area":"lr"},{"id":"2312.15194","title":"PokeMQA: Programmable knowledge editing for Multi-hop Question Answering","created":"2023-12-23","cited_by_count":23,"area":"lr"},{"id":"2403.03348","title":"Learning to Maximize Mutual Information for Chain-of-Thought Distillation","created":"2024-03-05","cited_by_count":23,"area":"lr"},{"id":"2207.12576","title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","created":"2022-07-25","cited_by_count":20,"area":"lr"},{"id":"2303.12513","title":"Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding","created":"2023-03-21","cited_by_count":20,"area":"lr"},{"id":"2310.18440","title":"Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement","created":"2023-10-27","cited_by_count":17,"area":"lr"},{"id":"2401.04181","title":"Language-Conditioned Robotic Manipulation with Fast and Slow Thinking","created":"2024-01-08","cited_by_count":17,"area":"lr"},{"id":"2402.15000","title":"Divide-or-Conquer? Which Part Should You Distill Your LLM?","created":"2024-02-22","cited_by_count":17,"area":"lr"},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16,"area":"lr"},{"id":"2209.14901","title":"DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing","created":"2022-09-29","cited_by_count":14,"area":"lr"},{"id":"2310.05030","title":"Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index","created":"2023-10-08","cited_by_count":14,"area":"lr"},{"id":"2308.04679","title":"Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA","created":"2023-08-09","cited_by_count":13,"area":"lr"},{"id":"2410.11087","title":"Locality Alignment Improves Vision-Language Models","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2404.11792","title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","created":"2024-04-17","cited_by_count":11,"area":"lr"},{"id":"2511.00330","title":"Sherlock: Reliable and Efficient Agentic Workflow Execution","created":"2025-11-01","cited_by_count":11,"area":"lr"},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2605.17497","title":"Self-Supervised On-Policy Distillation for Reasoning Language Models","created":"2026-05-17","cited_by_count":10,"area":"lr"},{"id":"2606.21994","title":"Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts","created":"2026-06-20","cited_by_count":10,"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":"2412.07906","title":"Rethinking Emotion Annotations in the Era of Large Language Models","created":"2024-12-10","cited_by_count":8,"area":"lr"},{"id":"2604.26573","title":"PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners","created":"2026-04-29","cited_by_count":8,"area":"lr"},{"id":"2606.29340","title":"PHF: Privileged Hidden Flow for On-Policy Self-Distillation","created":"2026-06-28","cited_by_count":8,"area":"lr"},{"id":"2206.07167","title":"Understanding Narratives through Dimensions of Analogy","created":"2022-06-14","cited_by_count":7,"area":"lr"},{"id":"2302.12569","title":"Implicit Temporal Reasoning for Evidence-Based Fact-Checking","created":"2023-02-24","cited_by_count":7,"area":"lr"},{"id":"2405.15551","title":"Thinking Forward: Memory-Efficient Federated Finetuning of Language Models","created":"2024-05-24","cited_by_count":7,"area":"lr"},{"id":"2502.13119","title":"STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2505.24181","title":"SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought","created":"2025-05-30","cited_by_count":7,"area":"lr"},{"id":"2506.11578","title":"Efficient LLM Collaboration via Planning","created":"2025-06-13","cited_by_count":7,"area":"lr"},{"id":"2509.06771","title":"D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning -- A Benchmark Dataset and Method","created":"2025-09-08","cited_by_count":7,"area":"lr"},{"id":"2510.11056","title":"From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"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":"2202.13529","title":"KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models","created":"2022-02-28","cited_by_count":6,"area":"lr"},{"id":"2408.11879","title":"Beyond Labels: Aligning Large Language Models with Human-like Reasoning","created":"2024-08-20","cited_by_count":6,"area":"lr"},{"id":"2305.14237","title":"HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"id":"2305.14864","title":"Just CHOP: Embarrassingly Simple LLM Compression","created":"2023-05-24","cited_by_count":5,"area":"lr"},{"id":"2410.03348","title":"Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning","created":"2024-10-04","cited_by_count":5,"area":"lr"},{"id":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"id":"2503.09820","title":"ViLAM: Distilling Vision-Language Reasoning into Attention Maps for Social Robot Navigation","created":"2025-03-12","cited_by_count":5,"area":"lr"},{"id":"2504.01738","title":"Style over Substance: Distilled Language Models Reason Via Stylistic Replication","created":"2025-04-02","cited_by_count":5,"area":"lr"},{"id":"2505.22137","title":"Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2512.21002","title":"Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation","created":"2025-12-24","cited_by_count":5,"area":"lr"},{"id":"2601.10109","title":"Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation","created":"2026-01-15","cited_by_count":5,"area":"lr"},{"id":"2603.13765","title":"Knowledge Distillation for Large Language Models","created":"2026-03-14","cited_by_count":5,"area":"lr"},{"id":"2306.09918","title":"No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference","created":"2023-06-16","cited_by_count":4,"area":"lr"},{"id":"2402.09051","title":"FGeo-DRL: Deductive Reasoning for Geometric Problems through Deep Reinforcement Learning","created":"2024-02-14","cited_by_count":4,"area":"lr"},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2508.00378","title":"CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding","created":"2025-08-01","cited_by_count":4,"area":"lr"},{"id":"2604.02819","title":"Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2402.01812","title":"Distilling LLMs' Decomposition Abilities into Compact Language Models","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2410.22372","title":"A Hierarchical Language Model For Interpretable Graph Reasoning","created":"2024-10-29","cited_by_count":3,"area":"lr"},{"id":"2507.05707","title":"Agentic-R1: Distilled Dual-Strategy Reasoning","created":"2025-07-08","cited_by_count":3,"area":"lr"},{"id":"2509.22921","title":"Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2601.11047","title":"CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs","created":"2026-01-16","cited_by_count":3,"area":"lr"},{"id":"2603.21701","title":"Rethinking Token Reduction for Large Vision-Language Models","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2606.03705","title":"Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs","created":"2026-06-02","cited_by_count":3,"area":"lr"},{"id":"2606.10385","title":"Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation","created":"2026-06-09","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":"2607.21550","title":"X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment","created":"2026-07-23","cited_by_count":3,"area":"lr"},{"id":"2607.22629","title":"Masked Distillation: Internalizing the Chain-of-Thought in Language Models","created":"2026-06-18","cited_by_count":3,"area":"lr"},{"id":"2210.01258","title":"Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes","created":"2022-10-03","cited_by_count":2,"area":"lr"},{"id":"2312.11720","title":"Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models","created":"2023-12-18","cited_by_count":2,"area":"lr"},{"id":"2401.02187","title":"Location Aware Modular Biencoder for Tourism Question Answering","created":"2024-01-04","cited_by_count":2,"area":"lr"},{"id":"2412.20227","title":"LLM Reasoning Engine: Specialized Training for Enhanced Mathematical Reasoning","created":"2024-12-28","cited_by_count":2,"area":"lr"},{"id":"2506.03921","title":"Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning","created":"2025-06-04","cited_by_count":2,"area":"lr"},{"id":"2506.08364","title":"Structure-Augmented Reasoning Generation","created":"2025-06-10","cited_by_count":2,"area":"lr"},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2512.00881","title":"Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing","created":"2025-11-30","cited_by_count":2,"area":"lr"},{"id":"2601.08108","title":"Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2609.22254","title":"Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation","created":"2026-09-06","cited_by_count":2,"area":"lr"},{"id":"2210.00858","title":"Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach","created":"2022-10-03","cited_by_count":1,"area":"lr"},{"id":"2212.09721","title":"KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales","created":"2022-12-19","cited_by_count":1,"area":"lr"},{"id":"2307.01644","title":"Insert-expansions for Tool-enabled Conversational Agents","created":"2023-07-04","cited_by_count":1,"area":"lr"},{"id":"2406.13808","title":"Can Low-Rank Knowledge Distillation in LLMs be Useful for Microelectronic Reasoning?","created":"2024-06-19","cited_by_count":1,"area":"lr"},{"id":"2411.15281","title":"ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation","created":"2024-11-22","cited_by_count":1,"area":"lr"},{"id":"2412.17052","title":"ViLBias: Detecting and Reasoning about Bias in Multimodal Content","created":"2024-12-22","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}