NVIDIA researchers and collaborators release SoL-Pi
SoL-Pi released — it optimizes coding agents by running a recursive self-improvement loop at the harness layer. On GPT-5.6 Sol and Opus 5 it performed on par with Pi while cutting token traffic by 44.7–49.0% and API costs by about 1/3, reducing hourly cost by $8.75–13.50 versus native and by $4.36–5.71 versus Pi. It identified four mechanisms — action execution, context compression, observation handling and delegated reading — and confirmed transfer on EdgeBench, with 51 tasks.
Why it matters
The key is that the target of self-improvement is the harness configuration, not the model weights — a measurement showing there is still room to cut costs by a third with the same model.
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2609.20519Added in Week 39, 2026 · See that week