Nvidia's SoL-Pi cuts coding agent token usage by up to 49% by optimizing the harness
The Decoder · rss · 2026-09-26
The Decoder reports Nvidia's SoL-Pi, which cuts coding agents' token usage by up to 49% with little performance change by optimizing the control layer (harness) between the model and its environment rather than the model itself. A research agent tested 152 approaches across 3,000+ runs; gains were smaller on other benchmarks, suggesting task-dependent benefits.
More from coding & agent
- Sydney Codex Community Buildathon set for Nov 14 with Cerebras-backed ultrafast compute track — paw_lean · 2026-11-11
- shadcn's improve hits 10k stars: let top models plan, cheap models execute code fixes — shadcn · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11
- Claude Opus 5.5 runs an architecture search and finds AttnRes-Canon, a new top Transformer design — SonglinYang4 · 2026-11-11
- 5 research habits worth knowing: read papers backwards, reproduce first, wire coding agents via MCP — cneuralnetwork · 2026-11-11
- 'Adam can now do CAE': AI agent showcase in engineering simulation draws buzz — burhop · 2026-11-11