Why does chain-of-thought (CoT) reasoning work? A paper submitted to arXiv on October 18, "Visual Scaffolding: Toward Native Multimodal Reasoning," offers a useful lens: the success of CoT can be attributed to a textual scaffolding effect — explicit intermediate results can be examined, reused, and composed to support subsequent reasoning, much like scaffolding supports a building under construction. Mainstream multimodal LLMs, however, share an obvious blind spot: visual distinctions that are hard to express in concise verbal descriptions have never had an equivalent scaffold.
Visual features join the chain of thought
The paper defines native multimodal reasoning as reasoning in which native visual representations and language jointly carry reusable intermediate states. In the implementation, the model can autonomously initiate a retrieval action at any reasoning step; a lightweight retriever selects native visual features and incorporates them directly into the evolving CoT, where they remain available to subsequent steps — instead of "glance at the image once, then narrate everything in text."
What 88M parameters buy
Evaluation uses the team's own NMR-Bench, comprising Burden Counting and Path Tracing. With about 88M added parameters (around 2%) on top of Qwen3-VL-4B-Thinking, the model reaches 66.43% and 72.50% accuracy respectively; the paper reports this surpasses its evaluated GPT-5.5 and Gemini 3.1 Pro baselines. One caveat: it is a self-built benchmark, and as of this writing our search found no independent third-party replication, so treat cross-model rankings with some caution.
The more convincing part is the intervention analysis: with the intervening text held fixed, changing the selected visual content affects task accuracy and can even redirect subsequent visual selection — evidence that visual states genuinely function as reasoning material rather than input-stage decoration.
So what
The value of this work lies in its direction, not its leaderboard lines. Today's mainstream multimodal models essentially squeeze visual information into verbally expressible channels; whatever doesn't fit is lost. If native visual representations can become first-class citizens alongside language, the same logic extends to audio, video, and sensor signals. For teams building agents, "what representation do you store intermediate state in" is a question worth answering now. The paper is at arXiv:2610.25247.