MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation

• URL: http://arxiv.org/abs/2506.17113v1
• Date: Fri, 20 Jun 2025 16:14:13 GMT
• Title: MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation
• Authors: Shoubin Yu, Yue Zhang, Ziyang Wang, Jaehong Yoon, Mohit Bansal,
• Abstract summary: MEXA is a training-free framework that performs modality- and task-aware aggregation of expert models.<n>We evaluate our approach on diverse multimodal benchmarks, including Video Reasoning, Audio Reasoning, 3D Understanding, and Medical QA.
• Score: 64.85885900375483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance, medical diagnosis requires precise reasoning over structured clinical tables, while financial forecasting depends on interpreting plot-based data to make informed predictions. To tackle this challenge, we introduce MEXA, a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse and distinct domains. MEXA dynamically selects expert models based on the input modality and the task-specific reasoning demands (i.e., skills). Each expert model, specialized in a modality task pair, generates interpretable textual reasoning outputs. MEXA then aggregates and reasons over these outputs using a Large Reasoning Model (LRM) to produce the final answer. This modular design allows flexible and transparent multimodal reasoning across diverse domains without additional training overhead. We extensively evaluate our approach on diverse multimodal benchmarks, including Video Reasoning, Audio Reasoning, 3D Understanding, and Medical QA. MEXA consistently delivers performance improvements over strong multimodal baselines, highlighting the effectiveness and broad applicability of our expert-driven selection and aggregation in diverse multimodal reasoning tasks.

Related papers

• Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective [42.832839189236694]
  We propose MAMMQA, a multi-agent QA framework for multimodal inputs spanning text, tables, and images.<n>Our system includes two Visual Language Model (VLM) agents and one text-based Large Language Model (LLM) agent.<n> Experiments on diverse multimodal QA benchmarks demonstrate that our cooperative, multi-agent framework consistently outperforms existing baselines in both accuracy and robustness.
  arXiv  Detail & Related papers  (2025-05-27T07:23:38Z)
• Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning [76.10639521319382]
  We propose Symbolic-MoE, a symbolic, text-based, and gradient-free Mixture-of-Experts framework.<n>We show that Symbolic-MoE's instance-level expert selection improves performance by a large margin but -- when implemented naively -- can introduce a high computational overhead.
  arXiv  Detail & Related papers  (2025-03-07T18:03:13Z)
• MIND: Modality-Informed Knowledge Distillation Framework for Multimodal Clinical Prediction Tasks [50.98856172702256]
  We propose the Modality-INformed knowledge Distillation (MIND) framework, a multimodal model compression approach.<n>MIND transfers knowledge from ensembles of pre-trained deep neural networks of varying sizes into a smaller multimodal student.<n>We evaluate MIND on binary and multilabel clinical prediction tasks using time series data and chest X-ray images.
  arXiv  Detail & Related papers  (2025-02-03T08:50:00Z)
• Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark [73.27104042215207]
  We introduce EMMA, a benchmark targeting organic multimodal reasoning across mathematics, physics, chemistry, and coding.<n>EMMA tasks demand advanced cross-modal reasoning that cannot be addressed by reasoning independently in each modality.<n>Our evaluation of state-of-the-art MLLMs on EMMA reveals significant limitations in handling complex multimodal and multi-step reasoning tasks.
  arXiv  Detail & Related papers  (2025-01-09T18:55:52Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• FinVision: A Multi-Agent Framework for Stock Market Prediction [0.0]
  This research introduces a multi-modal multi-agent system designed specifically for financial trading tasks. A key feature of our approach is the integration of a reflection module, which conducts analyses of historical trading signals and their outcomes.
  arXiv  Detail & Related papers  (2024-10-29T06:02:28Z)
• HEMM: Holistic Evaluation of Multimodal Foundation Models [91.60364024897653]
  Multimodal foundation models can holistically process text alongside images, video, audio, and other sensory modalities. It is challenging to characterize and study progress in multimodal foundation models, given the range of possible modeling decisions, tasks, and domains.
  arXiv  Detail & Related papers  (2024-07-03T18:00:48Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• Towards Robust Multi-Modal Reasoning via Model Selection [7.6621866737827045]
  LLM serves as the "brain" of the agent, orchestrating multiple tools for collaborative multi-step task solving. We propose the $textitM3$ framework as a plug-in with negligible runtime overhead at test-time. Our experiments reveal that our framework enables dynamic model selection, considering both user inputs and subtask dependencies.
  arXiv  Detail & Related papers  (2023-10-12T16:06:18Z)

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.