SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Researchers introduced SoL-Pi, a method for recursively scaling auto-research loops to improve token efficiency in agent harnesses, according to the paper's headline and abstract. The work targets coding agents that operate in unattended, around-the-clock exploration, where work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback. The authors argue token efficiency is important for scaling recursive self-improvement.

As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback. Token efficiency therefore becomes important for scaling recursive self-improvement. We take an