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

TL;DR

GRAIL is a hybrid framework that enables real-time agent discovery with high accuracy and sub-400ms latency by combining specialized models, data augmentation, and fine-grained matching techniques.

Contribution

GRAIL introduces a novel hybrid approach with SLM-enhanced prediction, pseudo-document expansion, and MaxSim resonance for fast, accurate agent discovery.

Findings

Achieves over 79x reduction in discovery latency compared to LLM-based methods.

Outperforms traditional vector search in Recall@10 on AgentTaxo-9K dataset.

Validates effectiveness on a large-scale agent dataset with high accuracy and speed.

Abstract

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 \textbf{GRAIL} (Granular Resonance-based Agent/AI Link), a novel framework achieving sub-400ms discovery latency without compromising accuracy. GRAIL introduces three key innovations: (1) \textbf{SLM-Enhanced Prediction}, replacing the generalized LLM parser with a specialized, fine-tuned Small Language Model (SLM) for millisecond-level capability tag prediction; (2) \textbf{Pseudo-Document Expansion}, augmenting agent descriptions with synthetic queries to enhance semantic density for robust dense retrieval; and (3) \textbf{MaxSim Resonance}, a fine-grained matching mechanism computing maximum similarity between user queries and discrete agent usage examples, effectively mitigating semantic dilution. Validated on \textbf{AgentTaxo-9K}, our new large-scale dataset of 9,240 agents, GRAIL reduces end-to-end discovery latency by over \textbf{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."