让AI代理实时从经验中学习新操作，提升任务完成效率。
Real-Time Procedural Learning From Experience for AI Agents
- 用环境与内部状态匹配过往经验，实时检索可用操作范例。
- 在真实网页浏览任务中，准确率、可靠性与成本效率全面提升。
- 适合需要快速适应变化环境的AI代理应用。
从试错中实时学习是生物智能的标志，但大多数基于大语言模型的代理在部署后缺乏获取程序性知识的机制。我们提出一种轻量级后训练学习机制——基于状态索引的经验过程回忆（PRAXIS），通过联合匹配环境与内部状态，从历史经验中检索动作结果范例，并实时生成可复用的状态-动作-结果示例，增强代理决策能力。在REAL网页浏览基准测试中，PRAXIS在不同基础模型架构下均提升了任务完成准确率、可靠性和成本效率，并初步展现出对未见任务在相似环境中的泛化能力。结果表明，PRAXIS使AI代理能在动态变化的状态环境中有效学习新流程，推动其实际应用。
原文摘要 · Abstract (English)
Learning how to do things from trial and error in real time is a hallmark of biological intelligence, yet most LLM-based agents lack mechanisms to acquire procedural knowledge after deployment. We propose Procedural Recall for Agents with eXperiences Indexed by State (PRAXIS), a lightweight post-training learning mechanism that stores the consequences of actions and retrieves them by jointly matching environmental and internal states of past episodes to the current state. PRAXIS augments agentic action selection with retrieved state-action-result exemplars that are generated in real time. When evaluated on the REAL web browsing benchmark, PRAXIS improves task completion accuracy, reliability, and cost efficiency across different foundation model backbones, and shows preliminary generalization to unseen tasks in similar environments. These results demonstrate that PRAXIS enables the practical adoption of AI agents in fast-evolving stateful environments by helping them learn new procedures effectively.
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。