SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness· SoL-Pi：高效代理绑定的递归自研究循环
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 RSI-inspired approach at the harness layer, scaling auto-research loops across increasingly numerous and diverse environments for harness rollouts. At this scale, the process yields reusable improvements that transfer beyond their development setting, moving automated harness discovery toward production-level outcomes. Four mechanisms survive selection and form SoL-Pi, spanning action execution, context compaction, observation handling, and delegated reading. On the 51-task EdgeBench evaluation
SoL-Pi 通过递归自研究循环提高代理在多种环境中的执行效率。
- 核心方法
- 通过四种机制（动作执行、上下文压缩、观察处理和委托阅读）构建递归自研究循环（SoL-Pi），以提高代理的递归自改进效率。
- 适合谁读
- 适合研究者和工程师阅读，特别是关注自动化代理和递归自改进技术的读者。
- 要解决的问题
- 解决编码代理在无人监督的探索过程中，如何在多环境和多样化任务中高效递归自改进的问题。
- 关键实验
- 在 51 个任务的 EdgeBench 评估中进行了实验验证。
- 主要贡献
- 提出了一种高效的代理递归自改进框架 SoL-Pi，该框架在大规模环境中表现出色，并且改进成果可跨环境复用。
- 意义与局限
- 意义在于推动了自动化代理的发展，使其更接近生产环境的应用；局限性在于当前实验环境可能仍不够广泛，需要进一步验证。