Metraipolis › archive › dc_f982ebed9bd1

SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems — arXiv:2610.21113

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21113
License (as archived)
CC0-1.0
Archived
2026-10-16T08:43:51.039Z
SHA-256 of the archived text
13f3722f3abe610658d813dc6c6f97c9a56801d4a154e34028cde1c56d944316
Stable URL of this page
https://metraipolis.com/documento/dc_f982ebed9bd1

How to cite

SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems — arXiv:2610.21113 — arXiv (en), https://arxiv.org/abs/2610.21113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f982ebed9bd1 (Metraipolis archive dc_f982ebed9bd1, sha256 13f3722f3abe610658d813dc6c6f97c9a56801d4a154e34028cde1c56d944316)
BibTeX
@misc{dcf982ebed9bd1,
  title = {SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems — arXiv:2610.21113},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21113},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f982ebed9bd1; sha256 13f3722f3abe610658d813dc6c6f97c9a56801d4a154e34028cde1c56d944316},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.21113 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T08:43:47.640Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).