菜单

关于 🐙 GitHub
arXiv 提交日期: 2026-06-29
📄 Abstract - Parametric Skills

Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually authored or extracted from task trajectories, are textual recipes encoding mature problem-solving experience and are critical to agentic capabilities. Despite widespread deployment, their utility is limited by the model's ability to comprehend and follow skill instructions, especially under complex and long-context scenarios, where key instructions are difficult to locate and adhere to. To address this limitation, we propose ParametricSkills, a framework that can convert free-form textual skills into parameters at test time, enabling context-free skill exploitation. Specifically, we first construct a large-scale, high-quality skill library, and synthesize single-turn and multi-turn skill exploitation trajectories built around these skills with OpenCode. Using these data, we then train a hypernetwork that parameterizes both the skill content and the test-time exploitation methodology by receiving textual skills and converting them into LoRA adapters. Experimental results on six complex software engineering (SWE) subtasks demonstrate that, the proposed ParametricSkills averagely outperforms in-context learning by 6.44 points as judged by DeepSeek-V4-Flash, while also achieving significantly higher BERT Score and F1 score, confirming its effectiveness. Beyond performance, we further find that parametric skills, being inherently accumulative, offer a preliminary yet promising avenue toward test-time continual learning.

顶级标签: llm model training agents
详细标签: parameter generation hypernetwork lora adapter skill transfer continual learning 或 搜索:

ParametricSkills:一种将自由文本技能转化为参数化知识的框架 / Parametric Skills


1️⃣ 一句话总结

ParametricSkills 提出通过超网络将自由形式的文本技能在测试时直接转换为 LoRA 适配器参数,从而克服了传统上下文学习在处理复杂长上下文时模型难以遵循指令的局限,并在软件工程任务上显著超越基线方法。


2️⃣ 论文创新点

1. 测试时超网络驱动的参数生成范式

2. 三阶段训练流程与自监督预训练目标

3. 双类型单轮技能利用样本构造

4. 多轮技能利用轨迹构造与验证

5. 基于秩拼接的加权技能合并方法

6. 自进化参数化技能循环

7. 基于指数移动平均(EMA)的持续学习机制


3️⃣ 主要结果与价值

结果亮点

实际价值


4️⃣ 术语表

源自 arXiv: 2606.30015