Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a framework that automatically constructs such reusable skills to enhance LLMs in tool use, multi-step reasoning, and dynamic environment interaction. To this end, we propose Collective Skill Tree Search (CSTS), a novel tree-search-based skill construction framework that constructs structured, diverse and generalizable tree of skills. The core idea of CSTS is to leverage collective intelligence to jointly search, identify and compose effective skills via two iterative phases: Collective Skill Node Generation (CSN-Gen) and Collective Skill Node Assessment (CSN-Assess). CSN-Gen exploits collective knowledge from multiple models to explore diverse candidate skills for each subtask, enabling comprehensive skill exploration. CSN-Assess employs multiple models as judges to evaluate and select skill nodes with two scoring mechanisms: (1) collective quality scoring that aggregates independent evaluations to produce a robust estimate of skill effectiveness, and (2) collective transferability scoring that explicitly verifies whether a skill generalizes well across different models. With CSTS, we construct a set of comprehensive tree of skills along with skill-augmented training data, enabling models to effectively learn and utilize skills. Besides, we introduce Collective Skill Reinforcement Learning, which actively selects multiple relevant skills from the tree to broaden solution-space exploration, avoid being trapped by a single skill and its resulting homogeneous or suboptimal solutions. As a result, our trained model, OpenClaw-Skill, exhibits outstanding agentic capabilities in long-horizon planning, tool use and generalization over challenging benchmarks.

翻译：装备大型语言模型（LLM）智能体以有效技能，对于在诸如OpenClaw等实际系统中解决复杂任务至关重要。本工作旨在开发一种能自动构建此类可复用技能的框架，以增强LLM在工具使用、多步推理及动态环境交互方面的能力。为此，我们提出集体技能树搜索（CSTS），这是一种基于树搜索的新型技能构建框架，可构建结构化、多样化且具有泛化能力的技能树。CSTS的核心思想是通过两个迭代阶段——集体技能节点生成（CSN-Gen）与集体技能节点评估（CSN-Assess）——利用集体智能联合搜索、识别并组合有效技能。CSN-Gen从多个模型中提取集体知识，为每个子任务探索多样化的候选技能，实现全面的技能探索；CSN-Assess则以多个模型作为评判者，通过两种评分机制评估并筛选技能节点：（1）集体质量评分，聚合独立评估结果以产生对技能有效性的稳健估计；（2）集体可迁移性评分，显式验证技能是否在不同模型间具有良好的泛化能力。借助CSTS，我们构建了一套全面的技能树及对应的技能增强训练数据，使模型能有效学习并运用技能。此外，我们引入集体技能强化学习，从技能树中主动选择多个相关技能以拓宽解空间探索，避免受困于单一技能及其导致的同质化或次优解。最终，我们训练的模型OpenClaw-Skill在长程规划、工具使用及对挑战性基准的泛化能力上展现出卓越的智能体能力。