# Large Language Models are Visual Reasoning Coordinators

arXiv: https://arxiv.org/abs/2310.15166 · HTML: https://mlsanity.com/paper/2310.15166/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 106 of its 125 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 106)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)

## Built on by (most cited first, 30 of 58)

- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Improving Multi-Agent Debate with Sparse Communication Topology](https://mlsanity.com/paper/2406.11776/) (2024)
- [Large Multimodal Agents: A Survey](https://mlsanity.com/paper/2402.15116/) (2024)
- [Embodied Understanding of Driving Scenarios](https://mlsanity.com/paper/2403.04593/) (2024)
- [Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey](https://mlsanity.com/paper/2402.05391/) (2024)
- [TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.01261/) (2023)
- [LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos](https://mlsanity.com/paper/2312.05269/) (2023)
- [TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems](https://mlsanity.com/paper/2311.11315/) (2023)
- [Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?](https://mlsanity.com/paper/2506.21215/) (2025)
- [Do Vision-Language Models Really Understand Visual Language?](https://mlsanity.com/paper/2410.00193/) (2024)
- [Explain Before You Answer: A Survey on Compositional Visual Reasoning](https://mlsanity.com/paper/2508.17298/) (2025)
- [Identifying and Mitigating Position Bias of Multi-image Vision-Language Models](https://mlsanity.com/paper/2503.13792/) (2025)
- [Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection](https://mlsanity.com/paper/2503.14853/) (2025)
- [PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model](https://mlsanity.com/paper/2401.06781/) (2024)
- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning](https://mlsanity.com/paper/2405.03272/) (2024)
- [Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models](https://mlsanity.com/paper/2311.17091/) (2023)
- [Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines](https://mlsanity.com/paper/2502.16641/) (2025)
- [VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation](https://mlsanity.com/paper/2311.16492/) (2023)
- [Grounding Language Models for Visual Entity Recognition](https://mlsanity.com/paper/2402.18695/) (2024)
- [A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis](https://mlsanity.com/paper/2511.00962/) (2025)
- [Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering](https://mlsanity.com/paper/2311.17331/) (2023)
- [Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering](https://mlsanity.com/paper/2505.10118/) (2025)
- [ClimateIQA: A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis](https://mlsanity.com/paper/2406.09838/) (2024)
- [Right this way: Can VLMs Guide Us to See More to Answer Questions?](https://mlsanity.com/paper/2411.00394/) (2024)
- [Re-Imagining Multimodal Instruction Tuning: A Representation View](https://mlsanity.com/paper/2503.00723/) (2025)
- [FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering](https://mlsanity.com/paper/2412.07030/) (2024)
- [MetaWild: A Multimodal Dataset for Animal Re-Identification with Environmental Metadata](https://mlsanity.com/paper/2501.13368/) (2025)
- [Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering](https://mlsanity.com/paper/2404.13947/) (2024)
- [AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?](https://mlsanity.com/paper/2412.03002/) (2024)

## Abstract (arXiv)

Visual reasoning requires multimodal perception and commonsense cognition of the world. Recently, multiple vision-language models (VLMs) have been proposed with excellent commonsense reasoning ability in various domains. However, how to harness the collective power of these complementary VLMs is rarely explored. Existing methods like ensemble still struggle to aggregate these models with the desired higher-order communications. In this work, we propose Cola, a novel paradigm that coordinates multiple VLMs for visual reasoning. Our key insight is that a large language model (LLM) can efficiently coordinate multiple VLMs by facilitating natural language communication that leverages their distinct and complementary capabilities. Extensive experiments demonstrate that our instruction tuning variant, Cola-FT, achieves state-of-the-art performance on visual question answering (VQA), outside knowledge VQA, visual entailment, and visual spatial reasoning tasks. Moreover, we show that our in-context learning variant, Cola-Zero, exhibits competitive performance in zero and few-shot settings, without finetuning. Through systematic ablation studies and visualizations, we validate that a coordinator LLM indeed comprehends the instruction prompts as well as the separate functionalities of VLMs; it then coordinates them to enable impressive visual reasoning capabilities.