SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems
3.40T1 sourcearXiv cs.MA
Source record
Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2610.21113.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryPaper proposing SSR (Structural Signal Retriever), a deterministic, training-free method for discovering agents in large multi-agent systems. It uses IDF-weighted structural signals and an Inverted Signal Index over Agent Card fields, cutting LLM input by 98.8% and orchestration latency by 70.9% at 1,000 agents.
Why it mattersAddresses the practical ceiling of stuffing agent registries into an LLM context. Concrete benchmarks make it usable as a reference point when designing multi-agent orchestration layers.
Cited by
No citations on record.