{"ID":6138138,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T07:57:38.474999683Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07117","arxiv_id":"2607.07117","title":"Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning","abstract":"In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image. Recent studies show that state-of-the-art multimodal large language models struggle with this setting, particularly due to limited compositional reasoning and sensitivity to prompt construction. In this work, we propose a Tree-of-Thoughts (ToT) reasoning framework for T2I-ICL that introduces a multi-stage reasoning and selection layer that generates, evaluates, and selects among multiple candidate hypotheses before constructing the final prompt for image synthesis. By exploring alternative reasoning branches and selecting a coherent interpretation, the proposed approach mitigates prompt ambiguity and compositional errors. We implement the proposed approach in a complete ToT-T2IICL inference pipeline and evaluate it on the CoBSAT benchmark. Both qualitative and quantitative results show that structured multi-branch reasoning leads to more consistent and semantically aligned image generation compared to baseline and Chain-of-Thought prompting strategies, without any additional training or fine-tuning.","short_abstract":"In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image. Recent studies show that state-of-the-art multimodal large language models struggle with this setting, particularly due to limited compositional reasoning and sen...","url_abs":"https://arxiv.org/abs/2607.07117","url_pdf":"https://arxiv.org/pdf/2607.07117v1","authors":"[\"Stepanida Alekseeva\",\"Jenifer Kalafatovich\",\"Seong-Whan Lee\"]","published":"2026-07-08T07:58:48Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}