{"total":37,"rows":[{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"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":"2505.05464","title":"Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging","created":"2025-05-08","cited_by_count":40,"area":"lr"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2608.19098","title":"Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation","created":"2026-08-19","cited_by_count":18,"area":"lr"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2506.10822","title":"ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization","created":"2025-06-12","cited_by_count":14,"area":"lr"},{"id":"2502.00997","title":"MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs","created":"2025-02-03","cited_by_count":13,"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":"2601.13572","title":"Behavior Knowledge Merge in Reinforced Agentic Models","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2510.10977","title":"Revisiting Model Interpolation for Efficient Reasoning","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2502.09056","title":"Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe","created":"2025-02-13","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":"2410.13699","title":"Unconstrained Model Merging for Enhanced LLM Reasoning","created":"2024-10-17","cited_by_count":7,"area":"lr"},{"id":"2505.17592","title":"AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model","created":"2025-05-23","cited_by_count":7,"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":"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":"2502.04030","title":"Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging","created":"2025-02-06","cited_by_count":4,"area":"lr"},{"id":"2509.01363","title":"Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic","created":"2025-09-01","cited_by_count":4,"area":"lr"},{"id":"2505.16151","title":"Training-Free Reasoning and Reflection in MLLMs","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2605.09584","title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","created":"2026-05-10","cited_by_count":3,"area":"lr"},{"id":"2502.12492","title":"Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation","created":"2025-02-18","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":"2512.07710","title":"Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2607.18026","title":"Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2608.11758","title":"AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention","created":"2026-08-12","cited_by_count":1,"area":"lr"},{"id":"2609.00746","title":"Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis","created":"2026-09-01","cited_by_count":1,"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":"2605.14386","title":"Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2608.06699","title":"AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models","created":"2026-08-07","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"}],"next_cursor":null}