Peking University's MAServeBench benchmarks LLM serving with multi-agent workloads
PekingUniversity · hf · 2026-11-03
Peking University introduces MAServeBench, modeling multi-agent LLM collaboration as a configurable workload dimension to evaluate serving systems and hardware. It abstracts workflows (spawn, fork-join, refinement loops, debate), stages (roles, execution control, context construction), and semantic trace organization (task/stage/session/operation levels), with reproducible dependency traces—filling the gap left by single-request workloads that cannot capture hierarchical multi-agent collaboration patterns.
More from Infra
- Apple Q4: $114.5B revenue up 12%, AI/Siri spending to squeeze margins — mitchdeg · 2026-11-03
- Darkbloom passes 1T tokens as Mac compute network pivots to CI/CD — gajesh · 2026-11-03
- OpenRouter Hits 100T Weekly Tokens; Surplus Jumps to 2.87T/Week in 4 Weeks — 0xJeff · 2026-11-03
- Claude Code caches are model-specific: switching models, compacting and idle time all bust the cache — shoumikgoswami · 2026-11-03
- Strata update doubles local inference speed for quad-R9700 setups: 70 to 140-160 tok/s — poofph · 2026-11-03
- Space-based distributed training gains traction as researchers push orbital datacenter vision — MillionInt · 2026-11-03