BunshinRL: Whole-Workspace Forking for Agentic Reinforcement Learning Rollouts
Organizations: University of California, San Diego, La Jolla, CA, USA · GenseeAI
Abstract
Agentic reinforcement learning (RL) rollouts interleave model reasoning with tool calls in persistent workspaces. Scaling these rollouts incurs substantial memory costs for concurrent environments, while slow tool calls delay entire rollout batches. We present BunshinRL, an agentic RL rollout system that exploits shared environment state and recurring tool calls through three techniques: memory sharing across environments, tool-prefix caching, and speculative tool execution. These techniques build on BunshinFork, a novel live whole-workspace forking mechanism for containers. BunshinFork reconstructs process trees, shares memory copy-on-write, and preserves file, communication, and GUI state, enabling cached-state reuse and rollback after incorrect speculation. We implement BunshinRL and BunshinFork through Linux kernel module and CRIU modifications. BunshinRL reduces peak memory by up to 43%, total memory consumption by up to 51%, and end-to-end rollout latency by 23%.
Figures & tables
Agentic RL
Agentic reinforcement learning trains AI agents to plan, use tools, and adapt through feedback from multi-step interactions.
See all 248 papers