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
- WebMCP draws developer buzz as a way to bring MCP into the browser — nickbaumann_ · 2026-09-18
- Demo: Claude with built-in Cowork and Artifacts builds a multiplayer game from one prompt — felixrieseberg · 2026-09-18
- Six Coding Agents Share the Same Plan Mode Shape but Split on Context After Approval — RunAI_Coder · 2026-09-18
- EvoSkill-GUI: training-free skill evolution lifts GUI agents by up to 16.2% — Bofan Chen · 2026-09-18
- Testing Non-Deterministic LLM Agent Pipelines with Property-Based Assertions — Repulsive_Sugar_5252 · 2026-09-18
- Developer: Listing Rules for AI Never Ends — Describe How the Answer Should Feel — gabriel1 · 2026-09-18