M$^3$-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering

• URL: http://arxiv.org/abs/2603.08369v1
• Date: Mon, 09 Mar 2026 13:32:25 GMT
• Title: M$^3$-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering
• Abstract summary: M3-ACE is a multi-agentic context engineering framework designed to rectify visual perception in math reasoning.<n>Our method establishes new state-of-the-art results 89.1 on the MathVision benchmark and achieves consistent improvements on other related datasets.
• Score: 10.491266031106774
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multimodal large language models have recently shown promising progress in visual mathematical reasoning. However, their performance is often limited by a critical yet underexplored bottleneck: inaccurate visual perception. Through systematic analysis, we find that the most failures originate from incorrect or incomplete visual evidence extraction rather than deficiencies in reasoning capability. Moreover, models tend to remain overly confident in their initial perceptions, making standard strategies such as prompt engineering, multi-round self-reflection, or posterior guidance insufficient to reliably correct errors. To address this limitation, we propose M3-ACE, a multi-agentic context engineering framework designed to rectify visual perception in multimodal math reasoning. Instead of directly aggregating final answers, our approach decouples perception and reasoning by dynamically maintaining a shared context centered on visual evidence lists. Multiple agents collaboratively contribute complementary observations, enabling the system to expose inconsistencies and recover missing perceptual information. To support stable multi-turn collaboration, we further introduce two lightweight tools: a Summary Tool that organizes evidence from different agents into consistent, complementary, and conflicting components, and a Refine Tool that filters unreliable samples and guides iterative correction. Extensive experiments demonstrate that M3-ACE substantially improves visual mathematical reasoning performance across multiple benchmarks. Our method establishes new state-of-the-art results 89.1 on the MathVision benchmark and achieves consistent improvements on other related datasets, including MathVista and MathVerse. These results highlight the importance of perception-centric multi-agent collaboration for advancing multimodal reasoning systems.

Related papers

• Fine-Grained Multi Image Object Hallucination Benchmark [24.355918575761606]
  We introduce MIOH, a fine-grained multi-image object hallucination benchmark.<n>Through evaluation of 29 models, we reveal that even state-of-the-art systems like GPT-5 and Gemini-2.5-Pro exhibit distinct failure patterns.<n>MIOH serves as a critical evaluation tool for developing more reliable multimodal AI systems.
  arXiv  Detail & Related papers  (2026-08-31T11:53:03Z)
• Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts [58.86896791968143]
  Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks.<n>We identify a puzzling phenomenon termed Seeing but Not Thinking: models accurately perceive image content yet fail in subsequent reasoning.<n>We propose the Routing Distraction hypothesis: when processing visual inputs, the routing mechanism fails to adequately activate task-relevant reasoning experts.
  arXiv  Detail & Related papers  (2026-04-09T17:59:44Z)
• Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization [89.68681087743876]
  Multimodal Large Language Models (MLLMs) have incentivized models to think with images'' by actively invoking visual tools during multi-turn reasoning.<n>The common Reinforcement Learning practice of relying on outcome-based rewards ignores the fact that textual plausibility often masks executive failure.<n>We introduce Multimodal Agentic Policy Optimization (MAPO), bridging the gap between textual reasoning and visual actions generated by models within their Multimodal Chain-of-Thought.
  arXiv  Detail & Related papers  (2026-04-08T07:48:07Z)
• Deconstructing Multimodal Mathematical Reasoning: Towards a Unified Perception-Alignment-Reasoning Paradigm [82.57296908195654]
  Multimodal Mathematical Reasoning (MMR) has attracted increasing attention for its capability to solve mathematical problems that involve both textual and visual modalities.<n>Current models still face significant challenges in real-world visual math tasks.
  arXiv  Detail & Related papers  (2026-03-09T12:11:00Z)
• Perception-Aware Multimodal Spatial Reasoning from Monocular Images [57.42071289037214]
  spatial reasoning from monocular images is essential for autonomous driving.<n>Current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception.<n>We propose a perception-aware multimodal reasoning framework that equipsVLMs with explicit object-centric grounding ability.
  arXiv  Detail & Related papers  (2026-03-07T02:05:12Z)
• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? [50.92401586025528]
  Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear.<n>We introduce UniG2U-Bench, a comprehensive benchmark categorizing generation-to-understanding (G2U) evaluation into 7 regimes and 30 subtasks.
  arXiv  Detail & Related papers  (2026-03-03T18:36:16Z)
• Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images [53.373427633330515]
  We propose DRIM, a model that enables deep but reliable multi-turn reasoning when thinking with images in its multimodal CoT.<n>Based on a high-resolution image dataset, we construct high-difficulty and verifiable visual question-answer pairs.<n>In the SFT stage, we collect tool trajectories as cold-start data, guiding a multi-turn reasoning pattern.<n>In the RL stage, we introduce redundancy-penalized policy optimization, which incentivizes the model to develop a self-reflective reasoning pattern.
  arXiv  Detail & Related papers  (2025-12-19T07:44:43Z)
• ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning [103.7657839292775]
  ARM-Thinker is an Agentic multimodal Reward Model that autonomously invokes external tools to ground judgments in verifiable evidence.<n>We train ARM-Thinker with multi-stage reinforcement learning, jointly optimizing tool-calling decisions and judgment accuracy.<n>Our results demonstrate that agentic capabilities significantly enhance both accuracy and interpretability of reward models.
  arXiv  Detail & Related papers  (2025-12-04T18:59:52Z)
• What MLLMs Learn about When they Learn about Multimodal Reasoning: Perception, Reasoning, or their Integration? [46.836858357488296]
  Multimodal reasoning models have recently shown promise on challenging domains such as olympiad-level geometry.<n>We introduce MathLens, a benchmark designed to disentangle the subskills of multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-02T06:58:29Z)
• Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation [38.740533834549716]
  We show that language-only models can achieve comparable or even better performance than MLLMs that consume raw visual inputs.<n>Motivated by this, we propose a simple visual perturbation framework that enhances perceptual robustness without requiring algorithmic modifications.<n>Our findings highlight the critical role of visual perturbation in multimodal mathematical reasoning.
  arXiv  Detail & Related papers  (2025-06-11T13:39:46Z)
• Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
  We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-04-24T17:59:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.