AgentRec routes a natural-language prompt to the right LLM agent by embedding the prompt and comparing it with per-agent prompt embeddings, reaching 92.2% top-1 accuracy on a synthetic test set.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback
AgentRec routes a natural-language prompt to the right LLM agent by embedding the prompt and comparing it with per-agent prompt embeddings, reaching 92.2% top-1 accuracy on a synthetic test set.