mlsanityData to 14 Oct 2026

MCP: A Control-Theoretic Orchestration Framework for Synergistic Efficiency and Interpretability in Multimodal Large Language Models

arXiv 2509.16597 ↗First posted 20 Sep 2025cs.CLcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

Aiming at the problems of computational inefficiency and insufficient interpretability faced by large models in complex tasks such as multi-round reasoning and multi-modal collaboration, this study proposes a three-layer collaboration framework based on model-controller-task adaptation (MCP). By decoupling large model functions into reasoning, generation and retrieval modules, and combining reinforcement learning-driven dynamic routing algorithms and task adaptation mechanisms, the systematic integration of control theory and large model dynamic reasoning is achieved for the first time. Experiments show that the MCP framework improves the performance of cross-modal benchmarking tasks, such as GLUE, COCO, ScienceQA, etc., by 15-30% compared with the baseline model, improves the reasoning efficiency by 40%, and generates the interpretable intermediate results through the Presenter layer, obtaining 90% of the manual interpretability scores, which provides a brand-new technological path to solve the bottleneck of the practical application of the large model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 13 of its 19 references that are in the map. First posted on arXiv 20 Sep 2025.

Builds on

13 of 19 references.

References · 13

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  5. 2015Continuous control with deep reinforcement learningcited by 3,407
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  7. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  8. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  9. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  10. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
  11. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  12. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
1 more
  1. 2023Layer-adaptive Structured Pruning Guided by Latencycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models
  2. 2023Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning
  3. 2025ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
  4. 2025MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
  5. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
  6. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
  7. 2026Training Language Models to Cooperate with Inference-Time Controllers
  8. 2025Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models