Trace：一個分類學引導的多領域視覺推理環境

摘要

可驗證獎勵強化學習（RLVR）已大幅改善語言模型的推理能力，然而其延伸至視覺語言模型仍受限於缺乏同時具備廣泛性、可精確驗證且可再現的訓練資料。我們提出Trace，一個由分類學引導的多領域視覺推理環境。Trace將任務建構分解為場景語法與可執行任務程式，從而將視覺實現與答案計算分離。一個共享的語義狀態決定了渲染影像、提示、類型化答案、驗證器狀態與可重播的實例軌跡。最終環境涵蓋277個場景語法與11個視覺領域中的1,000個任務，並具有受控的語義與視覺變異。在64,000個Trace實例上進行可驗證獎勵強化學習，使得Qwen2.5-VL-3B在24個外部基準上的巨集平均提升了3.51個百分點，Qwen2.5-VL-7B提升了4.06個百分點，此結果證明了廣泛的程序化訓練能夠遷移至生成任務分佈之外。專案頁面：https://maveryn.github.io/trace/。

English

Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its extension to vision-language models remains constrained by the lack of training data that are simultaneously broad, exactly verifiable, and reproducible. We introduce Trace, a taxonomy-guided environment for multidomain visual reasoning. Trace factorizes task construction into a scene grammar and an executable task program, separating visual realization from answer computation. A shared semantic state determines the rendered image, prompt, typed answer, verifier state, and replayable instance trace. The resulting environment comprises 1,000 tasks over 277 scene grammars and 11 visual domains, with controlled semantic and visual variation. RLVR on 64,000 Trace instances improves the macro-average across 24 external benchmarks by 3.51 percentage points for Qwen2.5-VL-3B and 4.06 points for Qwen2.5-VL-7B, providing evidence that broad procedural training can transfer beyond the generated task distributions. Project page: https://maveryn.github.io/trace/.