用程序化技能学习降低智能体成本，提升效率与稳定性。
Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
- 将技能视为可执行程序，实现确定性动作序列
- 在三个环境中均显著降低推理成本并提升性能
- 适合关注智能体效率与长时稳定性的研究者
近期，通过技能增强大模型智能体能力的做法日益普遍。本文探索以技能学习方式高效适配智能体至新领域，重点在于成本效益而非单纯性能提升。我们提出：将技能视为程序的方法能最优降低代理成本。通过确定性执行动作序列，程序增强型智能体可可靠且低成本地达成目标，避免试错与长期行为退化。智能体可在推理时逐步发现并重构这些程序以应对未来任务。我们假设过往轨迹已蕴含足够信号，无需回放或验证即可指导技能学习，前提是智能体具备分析能力。为此，我们提出SpeedRunner——一种分析轨迹并优化技能的编码代理。在三个具身环境中的实验表明，SpeedRunner在学习效率和成本降低方面持续达到前沿水平，且对分布偏移和环境随机性保持鲁棒性。
原文摘要 · Abstract (English)
Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel domains by means of learning skills. Existing works focus on performance gain over cost effectiveness. As a result, little is known about what skill learning strategies save cost. We argue that among all the different skill learning methods, those that view skills as programs can achieve the best cost reduction. By executing sequences of actions deterministically, a program-augmented agent can reliably and cheaply achieve goals that would otherwise require trial and error and risk degenerate behavior over long horizons. An agent can learn at inference time by incrementally discovering these programs and equipping them for future tasks. We hypothesize that past trajectories contain enough signal to guide skill learning, even without replay or validation, provided the agent can learn to analyze them. To test our claims, we propose SpeedRunner, a coding agent that analyzes trajectories and refactors skills for better performance on future tasks. Across three different embodied environments, we show that SpeedRunner consistently achieves the frontier in learning and cost reduction while remaining robust against distribution shifts and environmental randomness.
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。