SIA：基于约束与权重更新的自改进人工智能

摘要

人类是构建和改进AI的瓶颈。无论是模型本身，还是包裹模型的智能体，都依赖人类编写、调优和修正。让AI能够自主改进自身的长期目标仍未实现。两条主要独立的研究路线试图突破这一瓶颈。构架更新学派让元智能体重写特定任务智能体的支架（包括工具、提示词、重试逻辑和搜索流程），同时保持模型权重固定。测试时训练学派则使用手工设计的强化学习流水线，在任务反馈的基础上更新模型自身的权重，同时保持支架固定。这两条路线彼此孤立运作。我们提出SIA，一种自我改进循环：其中语言模型智能体（反馈智能体）同时更新特定任务智能体的支架和权重。我们在三个对比领域进行评估：中文法律罪名分类、底层GPU内核优化和单细胞RNA降噪。在所有三个基准测试中，联合使用两种杠杆的效果均优于仅更新支架。与初始基线相比，在LawBench上提升56.6%，GPU内核运行时间减少91.9%，降噪性能提升502%。支架更新使模型具备智能体能力，塑造其搜索和行动方式；而权重更新则建立起任何提示词或支架都无法灌输的领域直觉。

English

Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI that can figure out how to improve itself remains open. Two largely disjoint research lines attack this bottleneck. The harness-update school has a meta-agent rewrite the scaffold of a task-specific agent (its tools, prompts, retry logic, and search procedure) while the model weights are held fixed. The test-time training school uses hand-written RL pipelines to update the model's own weights on task feedback while the harness is held fixed. These two silos operate in isolation. We propose SIA, a self-improving loop in which a language-model agent (the Feedback-Agent) updates both the harness and the weights of a task-specific agent. We evaluate across three contrasting domains: Chinese legal charge classification, low-level GPU kernel optimisation, and single-cell RNA denoising. Combining both levers outperforms scaffold iteration alone on all three benchmarks. The gains are 56.6% on LawBench, 91.9% runtime reduction on GPU kernels, and 502% on denoising over the initial baseline. Harness updates make the model agentic, shaping how it searches and acts, while weight updates build the domain intuition that no prompt or scaffold can instil.