Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets 事件

Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets arXiv:2605.26165v1 Announce Type: cross Abstract: Agentic RAG systems that equip language models with dozens to hundreds of tool definitions face a critical resource conflict: tool schemas consume the same context window needed for retrieval-augmented generation. We present the first systematic study of this tool-context trade-off, evaluating 14 models spanning 1.5B-32B local models plus one frontier API model across