~/talk

Accelerating RL With AgentCube: Cloud Native Multi-Agent Collaboration

on YouTube 19m
Talkat KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 · 2026-09-07..09-09· [kubernetes]

speaker

name:Zhencheng Lee
links:none on file

resources

video:https://youtu.be/-Oo_ukwOJgE
slides:none on file

summary

AgentCube is a Kubernetes-native runtime for multi-agent reinforcement learning that creates and manages concurrent agent sessions via a unified API. It uses warm pools to rapidly provision isolated Pod sandboxes, integrates with Kubernetes and Volcano for scheduling, and supports agent tasks like inference, tool invocation, code execution, result processing, elastic scaling, session routing, resource reuse, secure isolation, and automatic cleanup to speed up high-concurrency, short-lived RL workloads.

AI-written summary · about

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.