Thinking with Drafting: Optical Decompression via Logical Reconstruction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915965160128512 |
|---|---|
| author | Wei, Jingxuan He, Honghao Jia, Caijun Li, Siyuan Sun, Zheng Xu, Yuhang Lin, Yuanyuan Sun, Linzhuang Wu, Yuchen Yu, Bihui Zhang, Xiangxiang Tan, Cheng |
| author_facet | Wei, Jingxuan He, Honghao Jia, Caijun Li, Siyuan Sun, Zheng Xu, Yuhang Lin, Yuanyuan Sun, Linzhuang Wu, Yuchen Yu, Bihui Zhang, Xiangxiang Tan, Cheng |
| contents | Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasoning tasks: optical perception systems transcribe symbols without capturing logical topology, while pixel-based generative models produce visual artifacts lacking mathematical exactness. To bridge this gap, we propose that reasoning over visual inputs be reconceptualized as optical decompression-the process of reconstructing latent logical structures from compressed visual tokens. Guided by the axiom that Parsing is Reasoning, we introduce Thinking with Drafting (TwD), which utilizes a minimalist Domain-Specific Language (DSL) as a grounding intermediate representation. Unlike standard approaches that hallucinate answers directly, TwD forces the model to draft its mental model into executable code, rendering deterministic visual proofs for self-verification. To validate this, we present VisAlg, a visual algebra benchmark. Experiments demonstrate that TwD serve as a superior cognitive scaffold. Our work establishes a closed-loop system where visual generation acts not as a creative output but as a logical verifier, offering a generalizable path for visual reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11731 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Thinking with Drafting: Optical Decompression via Logical Reconstruction Wei, Jingxuan He, Honghao Jia, Caijun Li, Siyuan Sun, Zheng Xu, Yuhang Lin, Yuanyuan Sun, Linzhuang Wu, Yuchen Yu, Bihui Zhang, Xiangxiang Tan, Cheng Computation and Language Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasoning tasks: optical perception systems transcribe symbols without capturing logical topology, while pixel-based generative models produce visual artifacts lacking mathematical exactness. To bridge this gap, we propose that reasoning over visual inputs be reconceptualized as optical decompression-the process of reconstructing latent logical structures from compressed visual tokens. Guided by the axiom that Parsing is Reasoning, we introduce Thinking with Drafting (TwD), which utilizes a minimalist Domain-Specific Language (DSL) as a grounding intermediate representation. Unlike standard approaches that hallucinate answers directly, TwD forces the model to draft its mental model into executable code, rendering deterministic visual proofs for self-verification. To validate this, we present VisAlg, a visual algebra benchmark. Experiments demonstrate that TwD serve as a superior cognitive scaffold. Our work establishes a closed-loop system where visual generation acts not as a creative output but as a logical verifier, offering a generalizable path for visual reasoning. |
| title | Thinking with Drafting: Optical Decompression via Logical Reconstruction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.11731 |