{"total":26,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"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":"2506.17219","title":"No Free Lunch: Rethinking Internal Feedback for LLM Reasoning","created":"2025-06-20","cited_by_count":37,"area":"lr"},{"id":"2505.14009","title":"Activation-Guided Consensus Merging for Large Language Models","created":"2025-05-20","cited_by_count":12,"area":"lr"},{"id":"2510.10977","title":"Revisiting Model Interpolation for Efficient Reasoning","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2602.22538","title":"RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format","created":"2026-02-26","cited_by_count":9,"area":"lr"},{"id":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2509.08814","title":"Merge-of-Thought Distillation","created":"2025-09-10","cited_by_count":7,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2508.03140","title":"RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior","created":"2025-08-05","cited_by_count":5,"area":"lr"},{"id":"2510.08987","title":"Towards Efficient Multimodal Unified Reasoning Model via Model Merging","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2601.10949","title":"MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement","created":"2026-01-16","cited_by_count":3,"area":"lr"},{"id":"2510.14387","title":"Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2511.02451","title":"Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2601.03506","title":"QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2601.05560","title":"ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging","created":"2026-01-09","cited_by_count":1,"area":"lr"},{"id":"2601.13992","title":"\"The Whole Is Greater Than the Sum of Its Parts\": A Compatibility-Aware Multi-Teacher CoT Distillation Framework","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2605.12419","title":"ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2512.07650","title":"Exploring Test-time Scaling via Prediction Merging on Large-Scale Recommendation","created":"2025-12-08","cited_by_count":0,"area":"lr"},{"id":"2601.21187","title":"FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2603.21705","title":"Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2607.14895","title":"Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2608.10447","title":"Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.25583","title":"GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning","created":"2026-08-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}