Research
Plan or Retrieve First? A Scale Study of Tool Discovery Architectures
Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant
Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant approach, which we term Retrieve-then-Plan (RtP), embeds the user query and retrieves similar tools via approximate nearest-neighbor search. We study an alternative Plan-then-Retrieve (PtR) paradigm in which the LLM first generates Abstract Tool Stubs (hypothesized function signatures describing needed capabilities) which then serve as retrieval queries against the registry. Evaluating on…
Related
- Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents
- MA-Bench: Measuring Operational Planning in Language Models
- TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
- PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
- The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs
Source: Apple ML Research | 2026-10-15