專家提示：逐步工具檢索改善規劃。

摘要

大型語言模型（LLMs）越來越被廣泛應用於複雜的多步規劃任務中，其中工具檢索（TR）步驟對於實現成功結果至關重要。用於TR的兩種主要方法是單步檢索，利用完整查詢，以及使用任務分解（TD）的順序檢索，其中完整查詢被分割為離散的原子子任務。雖然單步檢索缺乏處理“工具間依賴性”的靈活性，但TD方法需要保持“子任務-工具原子性對齊”，因為工具箱可能會動態演變。為了解決這些限制，我們引入了逐步工具檢索以改進規劃（ProTIP）框架。ProTIP是一個輕量級的、基於對比學習的框架，它在不需要明確要求子任務標籤的情況下隱式執行TD，同時保持子任務-工具原子性。在ToolBench數據集上，ProTIP以顯著的優勢勝過基於ChatGPT任務分解方法，實現了TR的Recall@K=10提高了24%，並且在計劃生成方面工具準確性提高了41%。

English

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes. Two prevalent approaches for TR are single-step retrieval, which utilizes the complete query, and sequential retrieval using task decomposition (TD), where a full query is segmented into discrete atomic subtasks. While single-step retrieval lacks the flexibility to handle "inter-tool dependency," the TD approach necessitates maintaining "subtask-tool atomicity alignment," as the toolbox can evolve dynamically. To address these limitations, we introduce the Progressive Tool retrieval to Improve Planning (ProTIP) framework. ProTIP is a lightweight, contrastive learning-based framework that implicitly performs TD without the explicit requirement of subtask labels, while simultaneously maintaining subtask-tool atomicity. On the ToolBench dataset, ProTIP outperforms the ChatGPT task decomposition-based approach by a remarkable margin, achieving a 24% improvement in Recall@K=10 for TR and a 41% enhancement in tool accuracy for plan generation.

專家提示：逐步工具檢索改善規劃。

ProTIP: Progressive Tool Retrieval Improves Planning

摘要

Support