# Ant Ling — M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning

- Company: Ant Ling (ant-ling.com)
- Announced: 2025-07-11
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://developer.ant-ling.com/en/blogs/m2-reasoning
- Record: https://forck.live/items/22349-m2-reasoning-empowering-mllms-with-unified-general-and-spatial-reasoning
- Subject: Ling / Ring / Ming
- Open weights: yes
- Models affected: M2-Reasoning-7B

Ant Ling released M2-Reasoning-7B, a multimodal large language model (MLLM) designed for both general and spatial reasoning. The model uses a data pipeline generating 294.2K high-quality samples and a dynamic multi-task training strategy with step-wise optimization and task-specific rewards. It sets new state-of-the-art results across eight benchmarks in general and spatial reasoning domains.

## Evidence

Verbatim from https://developer.ant-ling.com/en/blogs/m2-reasoning:

> We introduce M2-Reasoning-7B, a model designed to excel in both general and spatial reasoning. Our approach integrates two key innovations: (1) a novel data pipeline that generates 294.2K high-quality data samples (168K for cold-start fine-tuning and 126.2K for RLVR), which feature logically coherent reasoning trajectories and have undergone comprehensive assessment; and (2) a dynamic multi-task training strategy with step-wise optimization to mitigate conflicts between data, and task-specific rewards for delivering tailored incentive signals.

---

Record: https://forck.live/items/22349-m2-reasoning-empowering-mllms-with-unified-general-and-spatial-reasoning
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md