{"total":17,"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":"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":"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":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"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":"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":"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":"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":"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":"2510.13935","title":"Big Reasoning with Small Models: Instruction Retrieval at Inference Time","created":"2025-10-15","cited_by_count":1,"area":"lr"},{"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":"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":"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":"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"}],"next_cursor":null}