一个智能体统一进化技能选择、使用与提炼，提升任务完成率。
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
- 用单一策略联合优化技能三能力：选、用、提炼。
- 在ALFWorld和WebShop上超越现有基线模型。
- 适合研究多技能智能体协同进化的研究人员。
持续的技能库使语言模型智能体能够跨任务复用成功策略。维护此类库需要三项耦合能力：智能体选择相关技能，在执行中使用它，并从经验中提炼新技能。现有方法分别优化这些能力或使用独立奖励信号，导致进化不完整且相互冲突。我们提出Skill1框架，通过单一策略共同演化技能选择、利用和提炼，目标是实现共享的任务结果优化。该策略生成查询以检索技能库，重新排序候选技能进行选择，基于所选技能求解任务，并从执行轨迹中提炼新技能。所有学习均来自单一任务结果信号：低频趋势用于奖励选择，高频变化用于奖励提炼。在ALFWorld和WebShop上的实验表明，Skill1优于先前的基于技能和强化学习基线。训练动态证实了三能力的协同进化，消融实验显示移除任一信用信号均会削弱进化效果。
原文摘要 · Abstract (English)
A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and distills new skills from experience. Existing methods optimize these capabilities in isolation or with separate reward sources, resulting in partial and conflicting evolution. We propose Skill1, a framework that trains a single policy to co-evolve skill selection, utilization, and distillation toward a shared task-outcome objective. The policy generates a query to search the skill library, re-ranks candidates to select one, solves the task conditioned on it, and distills a new skill from the trajectory. All learning derives from a single task-outcome signal. Its low-frequency trend credits selection and its high-frequency variation credits distillation. Experiments on ALFWorld and WebShop show that Skill1 outperforms prior skill-based and reinforcement learning baselines. Training dynamics confirm the co-evolution of the three capabilities, and ablations show that removing any credit signal degrades the evolution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。