# CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval

arXiv: https://arxiv.org/abs/2502.20826 · HTML: https://mlsanity.com/paper/2502.20826/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 51 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

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

## Builds on (most cited first, 9 of 9)

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Vision-by-Language for Training-Free Compositional Image Retrieval](https://mlsanity.com/paper/2310.09291/) (2023)
- [Towards Better Chain-of-Thought Prompting Strategies: A Survey](https://mlsanity.com/paper/2310.04959/) (2023)
- [Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking](https://mlsanity.com/paper/2312.08924/) (2023)

## Built on by (most cited first, 16 of 16)

- [Chain-of-Thought Re-ranking for Image Retrieval Tasks](https://mlsanity.com/paper/2509.14746/) (2025)
- [ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval](https://mlsanity.com/paper/2602.01639/) (2026)
- [WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2602.23029/) (2026)
- [From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2504.17990/) (2025)
- [MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2507.12819/) (2025)
- [UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval](https://mlsanity.com/paper/2604.20318/) (2026)
- [FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2607.02284/) (2026)
- [SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2509.26012/) (2025)
- [Say Cheese! Detail-Preserving Portrait Collection Generation via Natural Language Edits](https://mlsanity.com/paper/2601.20511/) (2026)
- [Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2602.00813/) (2026)
- [Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval](https://mlsanity.com/paper/2606.00910/) (2026)
- [MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval](https://mlsanity.com/paper/2603.17360/) (2026)
- [Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2605.08389/) (2026)
- [MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2608.25305/) (2026)
- [Sketch2Inspire: Structure-Sensitive Evaluation for Product Retrieval](https://mlsanity.com/paper/2608.29364/) (2026)
- [From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2610.05993/) (2026)

## Abstract (arXiv)

Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images by integrating information from a composed query (reference image and modification text) without training samples. Existing methods primarily combine caption models and large language models (LLMs) to generate target captions based on composed queries but face various issues such as incompatibility, visual information loss, and insufficient reasoning. In this work, we propose CoTMR, a training-free framework crafted for ZS-CIR with novel Chain-of-thought (CoT) and Multi-scale Reasoning. Instead of relying on caption models for modality transformation, CoTMR employs the Large Vision-Language Model (LVLM) to achieve unified understanding and reasoning for composed queries. To enhance the reasoning reliability, we devise CIRCoT, which guides the LVLM through a step-by-step inference process using predefined subtasks. Considering that existing approaches focus solely on global-level reasoning, our CoTMR incorporates multi-scale reasoning to achieve more comprehensive inference via fine-grained predictions about the presence or absence of key elements at the object scale. Further, we design a Multi-Grained Scoring (MGS) mechanism, which integrates CLIP similarity scores of the above reasoning outputs with candidate images to realize precise retrieval. Extensive experiments demonstrate that our CoTMR not only drastically outperforms previous methods across four prominent benchmarks but also offers appealing interpretability.