NVIDIA's EdgeWise cuts long-horizon agent inference costs up to 62% via selective cloud delegation
nvidia · hf · 2026-10-16
NVIDIA's EdgeWise is an edge-cloud framework: a local SLM handles long-horizon agent tasks and selectively delegates critical steps to a cloud LLM. A step-level RL method jointly optimizes task solving and delegation without extra inference-time models, plus an external judge-based delegation strategy. It matches or beats pure-LLM execution while cutting inference cost up to 62% on SWE-Rebench and 34% on Terminal-Bench 2.1, with real workstation deployment.
More from coding & agent
- SpecAgent: small model drafts tool calls, large model verifies in parallel to cut latency — Zilin Wang · 2026-10-16
- Salesforce's CLIFT turns sparse judge feedback into rewards for open-source web agents — Salesforce · 2026-10-16
- Agent spots invalid SPF record and autonomously fixes it in Vercel DNS via browser — dkundel · 2026-10-16
- MCPJam engineer asks how to test if ChatGPT plugins actually see latest UI selection — Paoli99 · 2026-10-16
- ChatGPT revives unplayable 2000s game Bookworm on Mac and iPhone in 15 minutes — Shleemy_Pants · 2026-10-16
- Agentflow: open-source collective memory network for agents via FastMCP and pgvector — agentflow0328 · 2026-10-16