arXiv cs.MA· Giancarlo Maldonado C\'ardenas, Carlos A. Astudillo, Nelson L. S. da Fonseca·· 2 天前AI 评分23
SSR：面向 LLM 编排多智能体系统的可扩展 Agent 发现结构化信号检索器
SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems
AI 导读
研究者提出免训练确定性检索方法 SSR，用于从不断增长的注册表中发现合适的 Agent Card。在 1,000 个智能体规模下，SSR 相对全目录编排减少 LLM 输入 98.8%、编排延迟 70.9%；在 MS MARCO 上 ISI 将显式评分段落减少 96.8% 且保持检索效果。该方法通过 IDF 加权结构化词汇信号与倒排信号索引，维持紧凑候选上下文并避免全目录编排的运行故障。
正文 · 原文
Abstract:Large-scale multi-agent ecosystems require mechanisms for discovering suitable agents without exposing entire registries to a large language model (LLM) orchestrator. The challenge is not only to retrieve relevant Agent Cards from a growing registry, but also to maintain a compact candidate context, since each additional candidate increases prompt size, inference cost, latency, and the risk of exceeding the model context window. We formulate this problem as candidate-context scalability and propose the Structural Signal Retriever (SSR), our deterministic and training-free retrieval method designed for Agent Card discovery. SSR derives structural lexical signals from capability-bearing Agent Card fields, weights them using inverse document frequency (IDF), and uses an Inverted Signal Index (ISI) for selective candidate scoring. We evaluate SSR using a synthetic agent benchmark, a public MS MARCO adaptation, and end-to-end LLM orchestration. At 1,000 agents, SSR reduces LLM input by 98.8% and orchestration latency by 70.9% relative to full-catalog orchestration. On MS MARCO, IDF improves retrieval effectiveness within the structural representation, while the ISI preserves retrieval effectiveness and reduces explicitly scored passages by 96.8%. End-to-end experiments show that candidate pre-selection maintains a compact candidate context as registry size grows and avoids the operational failures observed with full-catalog orchestration. These results support SSR as an Agent-Card-native, traceable retrieval mechanism for candidate-context scalability.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.21113 [cs.MA] |
| (or arXiv:2610.21113v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21113 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Carlos Alberto Astudillo Trujillo [view email]
[v1]
Thu, 15 Oct 2026 02:16:12 UTC (1,811 KB)
来源：arXiv cs.MA · arxiv.org