RCR-Router selects role-relevant memory slices under token budgets for multi-agent LLM systems, reporting token savings and quality gains on HotPotQA, MuSiQue, and 2WikiMultihop, but several experimental claims are undercut by estimated or missing data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
RCR-Router selects role-relevant memory slices under token budgets for multi-agent LLM systems, reporting token savings and quality gains on HotPotQA, MuSiQue, and 2WikiMultihop, but several experimental claims are undercut by estimated or missing data.