ProTIP: Progressive Tool Retrieval Improves Planning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningRetrievalSimilar Papers 제목 키워드 기반
ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation
Text-to-Image (T2I) Diffusion Models (DMs) have shown impressive abilities in generating high-quality images based on simple text descriptions. However, as is common with many Deep Learning (DL) models, DMs are subject t…
TriFlow: A Progressive Multi-Agent Framework for Intelligent Trip Planning
Real-world trip planning requires transforming open-ended user requests into executable itineraries under strict spatial, temporal, and budgetary constraints while aligning with user preferences. Existing LLM-based agent…
Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
Fact-seeking question answering with large language models (LLMs) remains unreliable when answers depend on up-to-date or conflicting information. Although retrieval-augmented and tool-using LLMs reduce hallucinations, t…
Question AnsweringBeyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System
Biomedical agents promise to automate complex biological workflows, yet current systems face two fundamental bottlenecks: bioinformatics tools are highly heterogeneous in interfaces and execution environments, while agen…
Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planning
Effective tool pre-selection via retrieval is essential for AI agents to select from a vast array of tools when identifying and planning actions in the context of complex user queries. Despite its central role in plannin…