aDSL：透過聯合代理-程式設計實現代理式3D創作

摘要

程式化表示為3D內容創作提供了一個引人注目的範式，得以實現細粒度編輯、可解釋性與明確的結構控制。然而，依賴大型語言模型（LLMs）來編寫3D程式的代理式工作流程仍然脆弱，往往無法將高層級意圖轉化為一致的低層級幾何。我們將這種脆弱性歸因於現有程式化介面與LLM推理優勢之間的失配，後者偏好語義結構和空間關係，而非脆弱的數值選擇。在本文中，我們共同設計了一個以代理為中心的領域特定語言（aDSL）和一個角色專業化的多代理系統，以縮小這一差距。aDSL透過強調可組合性和空間推理來橋接語義邏輯與幾何約束；它使代理能夠透過關係運算符而非脆弱的絕對坐標來操控幾何。在aDSL的基礎上，我們的免訓練多代理系統遵循規劃-執行-評論迴圈，以分解請求、合成程式碼，並利用執行回饋迭代修復錯誤與約束違反。實驗表明，這種協同設計提升了穩健性、可控性和對使用者意圖的忠實度。我們的方法在文字到形狀和圖像到形狀任務上優於先前的基於LLM的基準方法，同時保留了明確結構、可編輯性與可解釋性。它還支援諸如關節物體創建和結構化場景組合等下游應用。我們的程式碼可於 https://github.com/sig-pku/aDSL 取得。

English

Programmatic representations provide a compelling paradigm for 3D content creation, enabling fine-grained edits, interpretability, and explicit structural control. Yet, agentic workflows that rely on large language models (LLMs) to author 3D programs remain brittle, often failing to translate high-level intent into consistent low-level geometry. We attribute this fragility to a mismatch between existing programmatic interfaces and the reasoning strengths of LLMs, which favor semantic structure and spatial relations over fragile numeric choices. In this paper, we jointly design an Agent-centric Domain-Specific Language (aDSL) and a role-specialized multi-agent system to close this gap. aDSL bridges semantic logic and geometric constraints by emphasizing composability and spatial reasoning; it enables agents to manipulate geometry through relational operators instead of brittle absolute coordinates. Building on aDSL, our training-free multi-agent system follows a Plan-Execute-Critic loop to decompose requests, synthesize code, and iteratively repair errors and constraint violations using execution feedback. Experiments show that this co-design improves robustness, controllability, and faithfulness to user intent. Our method outperforms prior LLM-based baselines on text-to-shape and image-to-shape tasks while preserving explicit structure, editability, and interpretability. It also enables downstream applications such as articulated object creation and structured scene composition. Our code is available at https://github.com/sig-pku/aDSL.