# yaotingwangofficial/Awesome-MCoT

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

Repository: https://github.com/yaotingwangofficial/Awesome-MCoT
Canonical: https://ross.abutalabs.com/products/awesome-mcot
Homepage: https://arxiv.org/abs/2503.12605
Language: TeX
License Family: other
Topics: chain-of-thought, cot, deepseek-r1, instruction-tuning, large-vision-language-model, mllm-reasoning, multimodal, multimodal-chain-of-thought, multimodal-large-language-models, openai-o1, reasoning, survey, mcts, slow-thinking, system-2
Last push: 2026-05-22T00:49:11+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 35, longevity 40
- inputs: {"age_days": 564, "days_push": 104, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1023, forks 34 (observed 2026-08-28T04:03:16.119123+00:00)

## What it is
An awesome-list repository accompanying the first systematic survey paper on Multimodal Chain-of-Thought (MCoT) reasoning (arXiv:2503.12605). It curates datasets, benchmarks, and methodologies for step-by-step reasoning in multimodal large language models across image, video, speech, audio, 3D, and structured data.

## Use cases
- find papers on multimodal chain-of-thought reasoning
- survey datasets and benchmarks for MLLM reasoning evaluation
- learn about slow-thinking and system-2 reasoning in vision-language models
- research MCoT methods for robotics or healthcare applications
- track recent work on multimodal reasoning like OpenAI o1 and DeepSeek-R1
- find MCTS-based reasoning approaches for multimodal LLMs

## When to choose
- you need a curated, taxonomy-organized reading list on multimodal CoT research
- you are writing a paper or literature review on MLLM reasoning
- you want datasets and benchmarks for training or evaluating multimodal reasoning

## When to avoid
- you need runnable code or a software library rather than a paper list
- you want a general (text-only) chain-of-thought resource
- you need production tooling for multimodal inference

## Facets
- artifact type: learning-resource
- maturity: active
- function: nlp, machine-learning, documentation
- domain: large-language-models, artificial-intelligence, computer-vision, tutorials, awesome-lists
- platform: cross-platform
- tags: awesome-list, survey-paper, chain-of-thought, multimodal-reasoning, mllm, research-taxonomy, benchmarks, slow-thinking

## Member repositories
- yaotingwangofficial/Awesome-MCoT (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:16.119123+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:08:40.738914+00:00, confidence not recorded.
  - readme: https://github.com/yaotingwangofficial/Awesome-MCoT (fetched 2026-08-28T04:03:16.119123+00:00, sha f4e1722969bc)
  - homepage: https://arxiv.org/abs/2503.12605 (fetched 2026-08-29T13:08:49.624063+00:00, sha 2c8940fb3246)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T13:08:49.633374+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T13:08:49.636816+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T13:08:49.638655+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T13:08:49.635197+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.