NVIDIA's SoL-Pi Cuts Coding Agent Token Traffic ~49% and API Cost by a Third
nvidia · hf · 2026-09-18
NVIDIA introduces SoL-Pi, an RSI-inspired approach that recursively scales auto-research loops at the harness layer, letting agents discover reusable harness improvements across increasingly diverse environments that transfer beyond their development setting. Four mechanisms survive selection, spanning action execution, context compaction, observation handling, and delegated reading.
On the 51-task EdgeBench evaluation, SoL-Pi matches Pi's performance across GPT-5.6 Sol and Opus 5 while:
- Reducing recorded token traffic by 44.7–49.0%
- Cutting API cost by about one third
- Saving an estimated $8.75–13.50 per hour versus native Codex and Claude Code harnesses, and $4.36–5.71 versus Pi
The work demonstrates that automated harness discovery via self-improving research loops can reach production-level outcomes.
More from coding & agent
- Orgo, a YC-backed platform giving AI agents their own cloud desktops, claims 1,000+ teams — Scobleizer · 2026-11-04
- Founder: Vibe-coded a PMF-successful product, then hired pro devs to fix the mess — sujingshen · 2026-11-04
- One prompt to audit cross-region traffic: dev cut trans-Atlantic latency by moving a service — DanielLockyer · 2026-11-04
- Agent silently completed only a quarter of a 200-module build and stalled waiting for confirmation — Promptmethus · 2026-11-04
- ChatGPT Agent mode can scan LinkedIn and Indeed and build a tailored job-application spreadsheet — nikola_mr64990 · 2026-11-04
- Blogger auto-applied to 500 jobs via ChatGPT and got 12 interview calls in 24 hours — nikola_mr64990 · 2026-11-04