MCP-Flow automates large-scale discovery of MCP servers and synthesizes training data to improve LLM agents' tool selection and function calling at scales far beyond prior manual efforts.
Each predicted parameter name is compared recursively with the corresponding ground-truth parameter, without requiring positional alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
MCP-Flow automates large-scale discovery of MCP servers and synthesizes training data to improve LLM agents' tool selection and function calling at scales far beyond prior manual efforts.