AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models
Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grows, a function-calling model must process more schemas, consume more prompt tokens, and distinguish among increasingly similar or irrelevant alternatives. We study a complementary systems strategy: reduce the candidate set before language-model inference while leaving the downstream model unchanged. We introduce AgentWeave, a deterministic pre-inference routing layer that constructs a bounded model-visible action space using eligibility, requirement, capability, and routing signals. We evaluate AgentWeave with a frozen BFCL-derived routing-p...
| Authors | Saurav Singla, Aarav Singla, Advik Gupta et al. |
|---|---|
| Primary category | cs.AI |
| Published | 24 August 2026 |
| Last updated at source | 24 August 2026 |
Connected in the knowledge graph
- sauravsingla08/AgentWeave-Tool-RoutingDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.