Saved in:
Bibliographic Details
Main Authors: Wang, Haoqing, Long, Xiang, Li, Ziheng, Xu, Yilong, Li, Tingguang, Tang, Yehui
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.12566
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912961024491520
author Wang, Haoqing
Long, Xiang
Li, Ziheng
Xu, Yilong
Li, Tingguang
Tang, Yehui
author_facet Wang, Haoqing
Long, Xiang
Li, Ziheng
Xu, Yilong
Li, Tingguang
Tang, Yehui
contents Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as coding or math. When a general multi-domain expert-level model is required, we need to carefully consider the collaboration of RLVR across different domains. The current state-of-the-art models mainly employ two different training paradigms for multi-domain RLVR: mixed multi-task RLVR and separate RLVR followed by model merging. However, most of the works did not provide a detailed comparison and analysis about these paradigms. To this end, we choose multiple commonly used high-level tasks (e.g., math, coding, science, instruction following, and agent) as our target domains and design extensive qualitative and quantitative experiments using open-source datasets. We find the RLVR across domains exhibits few mutual interferences, and reasoning-intensive domains demonstrate mutually synergistic effects. Furthermore, we analyze the internal mechanisms of mutual gains from the perspectives of weight space geometry, information constraints, model prediction behavior and self-verification. This project is named as M2RL that means Mixed multi-task training or separate training followed by model Merging for Reinforcement Learning, and the homepage is at https://github.com/Mosi-AI/M2RL.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12566
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
Wang, Haoqing
Long, Xiang
Li, Ziheng
Xu, Yilong
Li, Tingguang
Tang, Yehui
Artificial Intelligence
Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as coding or math. When a general multi-domain expert-level model is required, we need to carefully consider the collaboration of RLVR across different domains. The current state-of-the-art models mainly employ two different training paradigms for multi-domain RLVR: mixed multi-task RLVR and separate RLVR followed by model merging. However, most of the works did not provide a detailed comparison and analysis about these paradigms. To this end, we choose multiple commonly used high-level tasks (e.g., math, coding, science, instruction following, and agent) as our target domains and design extensive qualitative and quantitative experiments using open-source datasets. We find the RLVR across domains exhibits few mutual interferences, and reasoning-intensive domains demonstrate mutually synergistic effects. Furthermore, we analyze the internal mechanisms of mutual gains from the perspectives of weight space geometry, information constraints, model prediction behavior and self-verification. This project is named as M2RL that means Mixed multi-task training or separate training followed by model Merging for Reinforcement Learning, and the homepage is at https://github.com/Mosi-AI/M2RL.
title To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2602.12566