# 技能并非万能：面向大语言模型智能体的模型感知技能对齐

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-29 08:00
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmpw3ayog03zisluk3nx29wts
- 原文链接：https://arxiv.org/abs/2605.30723

## AI 摘要

研究表明，为智能体检索的外部技能效果高度依赖具体模型，同一技能可能对不同骨干模型产生相反影响。为此，论文提出MASA框架，可在不修改智能体权重的前提下为目标模型定制技能。MASA包含两个阶段：1）基于爬山法与UCB驱动的树搜索的层级技能进化流水线；2）一个轻量级模型条件技能重写器，可在单次前向传播中复现定制过程。在三个交互环境与四个骨干模型上的实验中，MASA取得了最佳整体性能，最优基线提升达25.8点。该重写器能泛化到未见任务与环境，以远低于大型教师LLM的推理成本实现稳定更优的表现。

## 正文

LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing skill libraries are typically treated as model-agnostic, reusing the same skill formulations across backbones with substantially different capacities and behaviors. However, our controlled experiments across multiple model scales show that skill effectiveness is strongly model-dependent: a skill that benefits one backbone can harm another. Motivated by this observation, we propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights. MASA operates in two stages: (1) a hierarchical skill evolution pipeline that iteratively rewrites general and task-specific skills using hill climbing and UCB-driven tree search, guided by environment feedback and model capability profiles; and (2) a lightweight model-conditioned skill rewriter trained on evolution trajectories to reproduce the adaptation in a single forward pass. Experiments across three interactive environments and four backbones show that MASA consistently achieves the best overall performance, with gains of up to 25.8 points over the strongest baseline. The learned rewriter further generalizes to unseen tasks and environments without additional search, consistently outperforming a much larger teacher LLM at a fraction of the inference cost.