Priority PayGo keeps multi-agent tutoring responses under 4 seconds even at 50 concurrent users, while costs stay below textbook prices per student.
DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latency and Cost of Multi-Agent Intelligent Tutoring at Scale
Priority PayGo keeps multi-agent tutoring responses under 4 seconds even at 50 concurrent users, while costs stay below textbook prices per student.