GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing

As the ecosystem of Large Language Model (LLM)-based agents expands rapidly, efficient and accurate Agent Discovery becomes a critical bottleneck for large-scale multi-agent collaboration. Existing approaches typically face a dichotomy: either relying on heavy-weight LLMs for intent parsing, leading to prohibitive latency (often exceeding 30 seconds), or using monolithic vector retrieval that sacrifices semantic precision for speed. To bridge this gap, we propose $\mathbf{\text{GRAIL}}$ (Granular Resonance-based Agent/AI Link), a novel framework achieving sub-400ms discovery latency without compromising accuracy. GRAIL introduces three key innovations: (1) $\mathbf{\text{SLM-Enhanced}}\mathbf{\text{Prediction}}$, replacing the generalized LLM parser with a specialized, fine-tuned Small Language Model (SLM) for millisecond-level capability tag prediction; (2) $\mathbf{\text{Pseudo-Document}}\mathbf{\text{Expansion}}$, augmenting agent descriptions with synthetic queries to enhance semantic density for robust dense retrieval; and (3) $\mathbf{\text{MaxSim}}\mathbf{\text{Resonance}}$, a fine-grained matching mechanism computing maximum similarity between user queries and discrete agent usage examples, effectively mitigating semantic dilution. Validated on $\mathbf{\text{AgentTaxo-9K}}$, our new large-scale dataset of 9,240 agents, GRAIL reduces end-to-end discovery latency by over $\mathbf{\text{79}}\times$ compared to LLM-parsing baselines, while significantly outperforming traditional vector search in Recall@10. This framework offers a scalable, industrial-grade solution for the real-time ``Internet of Agents."