組合機器的能動性設計

摘要

複雜機器的設計既是人類智慧的標誌，也是工程實踐的基石。鑑於大型語言模型（LLMs）的最新進展，我們探討這些模型是否也能學會創造。我們從組合式機器設計的角度來探討這個問題：這是一項任務，其中機器由標準化部件組裝而成，以滿足在模擬物理環境中的功能需求，如移動或操作。為了支持這項研究，我們引入了BesiegeField，這是一個基於機器建造遊戲Besiege的測試平台，它支持基於部件的構建、物理模擬和獎勵驅動的評估。利用BesiegeField，我們對最先進的LLMs進行了基準測試，並確定了成功所需的關鍵能力，包括空間推理、策略性組裝和指令遵循。由於當前的開源模型表現不足，我們探索了強化學習（RL）作為改進的途徑：我們策劃了一個冷啟動數據集，進行了RL微調實驗，並強調了在語言、機器設計和物理推理交叉領域中的開放挑戰。

English

The design of complex machines stands as both a marker of human intelligence and a foundation of engineering practice. Given recent advances in large language models (LLMs), we ask whether they, too, can learn to create. We approach this question through the lens of compositional machine design: a task in which machines are assembled from standardized components to meet functional demands like locomotion or manipulation in a simulated physical environment. To support this investigation, we introduce BesiegeField, a testbed built on the machine-building game Besiege, which enables part-based construction, physical simulation and reward-driven evaluation. Using BesiegeField, we benchmark state-of-the-art LLMs with agentic workflows and identify key capabilities required for success, including spatial reasoning, strategic assembly, and instruction-following. As current open-source models fall short, we explore reinforcement learning (RL) as a path to improvement: we curate a cold-start dataset, conduct RL finetuning experiments, and highlight open challenges at the intersection of language, machine design, and physical reasoning.

組合機器的能動性設計

Agentic Design of Compositional Machines

摘要

Support