Bridging Tool Dependencies and Domain Knowledge: A Graph-Based Framework for In-Context Planning

2025/10/28 by Liu, Shengjie, Dong, Li, Zhang, Zhenyu
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2510.24690

Abstract

We present a framework for uncovering and exploiting dependencies among tools and documents to enhance exemplar artifact generation. Our method begins by constructing a tool knowledge graph from tool schemas,including descriptions, arguments, and output payloads, using a DeepResearch-inspired analysis. In parallel, we derive a complementary knowledge graph from internal documents and SOPs, which is then fused with the tool graph. To generate exemplar plans, we adopt a deep-sparse integration strategy that aligns structural tool dependencies with procedural knowledge. Experiments demonstrate that this unified framework effectively models tool interactions and improves plan generation, underscoring the benefits of linking tool graphs with domain knowledge graphs for tool-augmented reasoning and planning.

Citations

• Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
• From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
• jina-embeddings-v3: Multilingual Embeddings With Task LoRA
• Tool-Planner: Task Planning with Clusters across Multiple Tools
• ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• PaLM: Scaling Language Modeling with Pathways
• Language Models are Few-Shot Learners

Related

• Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models
• ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph
• Graph RAG-Tool Fusion
• GTool: Graph Enhanced Tool Planning with Large Language Model
• Tool-Planner: Task Planning with Clusters across Multiple Tools