pith. sign in

arxiv: 2507.08306 · v1 · pith:57IYSYUL · submitted 2025-07-11 · cs.AI · cs.CL· cs.CV· cs.LG

M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning

pith:57IYSYULopen to challenge →

classification cs.AI cs.CLcs.CVcs.LG
keywords reasoningdataspatialgeneraldynamicm2-reasoning-7bmllmsmodels
0
0 comments X
read the original abstract

Recent advancements in Multimodal Large Language Models (MLLMs), particularly through Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced their reasoning abilities. However, a critical gap persists: these models struggle with dynamic spatial interactions, a capability essential for real-world applications. To bridge this gap, 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. This combination of curated data and advanced training allows M2-Reasoning-7B to set a new state-of-the-art (SOTA) across 8 benchmarks, showcasing superior performance in both general and spatial reasoning domains.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines

    cs.AI 2025-08 accept novelty 7.0

    GeoLaux is a new benchmark of 2186 long-step geometry problems requiring auxiliary lines, used to evaluate 23 MLLMs and reveal major drops in performance on complex tasks.

  2. MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models

    cs.CV 2026-05 unverdicted novelty 6.0

    MHPR is a multidimensional benchmark for LVLM human-centric perception-reasoning with C-RD, SFT-D, RL-D, T-D data tiers and ACVG pipeline, showing training gains on Qwen2.5-VL-7B to near-parity with larger models.

  3. Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM Training

    cs.CL 2026-02 unverdicted novelty 6.0

    Dual Tuning is a data curation method that jointly scores training examples for benefit and for reasoning-gain to choose between reasoning and direct-answer post-training modes for multimodal LLMs.

  4. Trust Region On-Policy Distillation

    cs.LG 2026-05 unverdicted novelty 5.0

    TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.