# COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models

arXiv: https://arxiv.org/abs/2510.11012 · HTML: https://mlsanity.com/paper/2510.11012/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 27 of 27)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Neural Logic Machines](https://mlsanity.com/paper/1904.11694/) (2019)
- [Logical Neural Networks](https://mlsanity.com/paper/2006.13155/) (2020)
- [Investigating the Catastrophic Forgetting in Multimodal Large Language Models](https://mlsanity.com/paper/2309.10313/) (2023)
- [Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models](https://mlsanity.com/paper/2406.14852/) (2024)
- [Revisiting the Role of Language Priors in Vision-Language Models](https://mlsanity.com/paper/2306.01879/) (2023)
- [Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs](https://mlsanity.com/paper/2305.06343/) (2023)
- [System-1.x: Learning to Balance Fast and Slow Planning with Language Models](https://mlsanity.com/paper/2407.14414/) (2024)
- [Coarse-to-Fine Concept Bottleneck Models](https://mlsanity.com/paper/2310.02116/) (2023)
- [MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models](https://mlsanity.com/paper/2410.09733/) (2024)
- [Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learning](https://mlsanity.com/paper/2402.05945/) (2024)
- [ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models](https://mlsanity.com/paper/2310.05872/) (2023)
- [CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models](https://mlsanity.com/paper/2402.15021/) (2024)
- [ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation](https://mlsanity.com/paper/2402.04492/) (2024)
- [Natural Language Inference Improves Compositionality in Vision-Language Models](https://mlsanity.com/paper/2410.22315/) (2024)
- [PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck](https://mlsanity.com/paper/2403.05297/) (2024)
- [Wolf: Dense Video Captioning with a World Summarization Framework](https://mlsanity.com/paper/2407.18908/) (2024)
- [Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models](https://mlsanity.com/paper/2412.08111/) (2024)

## Built on by (most cited first, 1 of 1)

- [Retrieving Counterfactuals Improves Visual In-Context Learning](https://mlsanity.com/paper/2603.16737/) (2026)

## Abstract (arXiv)

Compositional reasoning remains a persistent weakness of modern vision language models (VLMs): they often falter when a task hinges on understanding how multiple objects, attributes, and relations interact within an image. Multiple research works have attempted to improve compositionality performance by creative tricks such as improving prompt structure, chain of thought reasoning, etc. A more recent line of work attempts to impart additional reasoning in VLMs using well-trained Large Language Models (LLMs), which are far superior in linguistic understanding than VLMs to compensate for the limited linguistic prowess of VLMs. However, these approaches are either resource-intensive or do not provide an interpretable reasoning process. In this paper, we present 'COCO-Tree' - a novel approach that augments VLM outputs with carefully designed neurosymbolic concept trees learned from LLMs to improve VLM's linguistic reasoning. COCO-Tree's beam search-inspired reasoning process boosts compositionality performance and provides a rationale behind VLM predictions. Empirical results on four compositionality benchmarks, Winoground, EqBench, ColorSwap, and SugarCrepe, in seven different open-source VLMs with varying sizes, demonstrate that COCO-Tree significantly improves compositional generalization by 5-10% over baselines.