{"total":64,"rows":[{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316,"area":"lr"},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2506.08989","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":42,"area":"lr"},{"id":"2310.09343","title":"Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents","created":"2023-10-13","cited_by_count":41,"area":"lr"},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2411.00300","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","created":"2024-11-01","cited_by_count":41,"area":"rag"},{"id":"2401.15269","title":"Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models","created":"2024-01-27","cited_by_count":34,"area":"lr"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2505.07176","title":"Internet of Agents: Fundamentals, Applications, and Challenges","created":"2025-05-12","cited_by_count":31,"area":"agents"},{"id":"2405.15574","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","created":"2024-05-24","cited_by_count":30,"area":"ssm"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2401.16107","title":"Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis","created":"2024-01-29","cited_by_count":23,"area":"agents"},{"id":"2405.13179","title":"RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts","created":"2024-05-21","cited_by_count":23,"area":"rag"},{"id":"2505.02138","title":"Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation","created":"2025-05-04","cited_by_count":20,"area":"distill"},{"id":"2410.01524","title":"HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models","created":"2024-10-02","cited_by_count":19,"area":"distill"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"area":null},{"id":"2606.05718","title":"ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation","created":"2026-06-04","cited_by_count":12,"area":"distill"},{"id":"2402.11176","title":"KnowTuning: Knowledge-aware Fine-tuning for Large Language Models","created":"2024-02-17","cited_by_count":11,"area":null},{"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":"2601.09028","title":"OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG","created":"2026-01-13","cited_by_count":11,"area":"rag"},{"id":"2509.25758","title":"Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2403.08607","title":"MedInsight: A Multi-Source Context Augmentation Framework for Generating Patient-Centric Medical Responses using Large Language Models","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2504.15848","title":"Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2506.04565","title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2403.09750","title":"Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2406.06562","title":"Achieving Sparse Activation in Small Language Models","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2411.07611","title":"Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models","created":"2024-11-12","cited_by_count":4,"area":"lr"},{"id":"2512.18337","title":"Towards Efficient Agents: A Co-Design of Inference Architecture and System","created":"2025-12-20","cited_by_count":4,"area":"agents"},{"id":"2601.04574","title":"FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedback","created":"2026-01-08","cited_by_count":4,"area":"alignment"},{"id":"2506.02519","title":"Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuning","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2512.02716","title":"Menta: A Small Language Model for On-Device Mental Health Prediction","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2512.16236","title":"The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2605.29602","title":"CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning","created":"2026-05-28","cited_by_count":3,"area":"lr"},{"id":"2407.20248","title":"LAPIS: Language Model-Augmented Police Investigation System","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2409.05347","title":"TriplePlay: Enhancing Federated Learning with CLIP for Non-IID Data and Resource Efficiency","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2410.15889","title":"Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples","created":"2024-10-21","cited_by_count":2,"area":"distill"},{"id":"2501.13567","title":"K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor","created":"2025-01-23","cited_by_count":2,"area":"rag"},{"id":"2508.20324","title":"Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities","created":"2025-08-27","cited_by_count":2,"area":"agents"},{"id":"2404.03891","title":"Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning","created":"2024-04-05","cited_by_count":1,"area":"lr"},{"id":"2410.16924","title":"SleepCoT: A Lightweight Personalized Sleep Health Model via Chain-of-Thought Distillation","created":"2024-10-22","cited_by_count":1,"area":"lr"},{"id":"2502.11779","title":"Efficient Response Generation Strategy Selection for Fine-Tuning Large Language Models Through Self-Aligned Perplexity","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2503.02463","title":"It Helps to Take a Second Opinion: Teaching Smaller LLMs to Deliberate Mutually via Selective Rationale Optimisation","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2510.12032","title":"Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2510.13935","title":"Big Reasoning with Small Models: Instruction Retrieval at Inference Time","created":"2025-10-15","cited_by_count":1,"area":"lr"},{"id":"2606.24841","title":"Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2609.39982","title":"Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2610.14474","title":"RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation","created":"2026-10-10","cited_by_count":1,"area":"lr"},{"id":"2503.05620","title":"Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2603.08148","title":"Gradually Excavating External Knowledge for Implicit Complex Question Answering","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.08094","title":"MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2608.07965","title":"CyberAGENTS: Structured Autonomy for Agentic Gamified Learning in Cybersecurity","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2609.25643","title":"Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.33426","title":"TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2610.00332","title":"The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.16713","title":"Audit Before You Distill: A Controlled Workflow for Reasoning Transfer into Compact Medical Language Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}