2026
Tvcache: A Tool-Value Cache for Post-Training LLM Agents
ICML 2026poster
In RL post-training of LLM agents, calls to ex ternal tools take several seconds or even min- utes, leaving allocated GPUs idle and inflating post-training time and cost. While many tool invocations repeat across parallel rollouts and could in principle be cached, naively caching their outputs for r…