想用冻结模型提升agent性能？HSI让模型自己改写执行脚手架，在BabyAI等任务上涨了39个点，代码已开源，值得一看。
Hierarchical Self-Improvement (HSI) 框架提出让单个冻结的LLM在三个层级上运作：任务harness执行任务、evolver重写harness、meta-evolver重写evolver策略。在BALROG基准上以DeepSeek-V4-Flash-Preview为骨干，HSI在中等难度任务上比初始harness提升显著：BabyAI +39.3、Crafter +33.0、TextWorld +25.0、MiniHack +15.0（均为原始% Progress）。在BabaIsAI子套件上表现出强泛化，BreakStop最佳测试0.98、GoTo达1.00（来自20%未见分割）。当任务超出骨干能力（如NLE）时，harness进化无改善，揭示了反馈保真度和骨干能力两个边界。
Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses
Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the \emph{harness}---is typically treated as a fixed artifact after deployment. This work studies an alternative where the harness is \emph{task-specific and continuously evolvable}: each task family maintains its own harness, which is hot-swapped across iterations through a fixed task-injection seam and rewritten using environment feedback. We introduce \textbf{Hierarchical Self-Improvement (HSI)}, a framework in which a single frozen LLM $M$ operates across three hierarchical scopes: a task harness $H$ that executes tasks, an evolver that rewrites $H$, and a meta-evolver that rewrites the evolver's strategy code under a frozen outer anchor. A thinking-on/off design isolates the contribution of harness evolution by disabling reasoning during task execution while enabling it during self-modification. HSI is bounded by two factors: a \emph{feedback-fidelity bound}, since evolution requires informative reward signals to guide selection, and a \emph{backbone capability bound}, since harness redesign cannot overcome limitations of the frozen model. On BALROG with DeepSeek-V4-Flash-Preview as the frozen backbone, HSI achieves consistent gains over the initial harness on moderate-difficulty tasks ($+39.3$ on BabyAI, $+33.0$ on Crafter, $+25.0$ on TextWorld, and $+15.0$ on MiniHack, all in raw \% Progress), while obtaining strong held-out generalization on BabaIsAI sub-suites ($0.98$ best-test on BreakStop and $1.00$ on GoTo from a $20\%$ unseen split). On tasks beyond the backbone's capability (NLE), harness evolution provides no improvement. These results demonstrate task-specific harness evolution as a viable axis for improving frozen LLM agents under clear empirical limits. Code is available at https://github.com/TailinZhou/hsi.