达尔文记忆:一种无训练的自调节记忆系统用于GUI代理进化
Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
AI总结:
达尔文记忆系统通过自进化架构提升GUI代理的执行稳定性与成功率,无需额外训练或架构开销。
摘要:
多模态大语言模型(MLLM)代理有助于图形用户界面(GUI)自动化,但受限于上下文窗口的限制,在长周期、跨应用任务中表现不佳。虽然记忆系统提供了一种可行的解决方案,但现有范式难以适应动态的GUI环境,存在高层意图与低层执行之间的粒度不匹配问题,以及上下文污染问题,即静态积累的过时经验会驱使代理产生幻觉。为了解决这些瓶颈,我们提出了达尔文记忆系统(DMS),一种自进化架构,通过生存法则构建记忆作为动态生态系统。DMS将复杂轨迹分解为独立、可重用的单元,以实现组合灵活性,并实现以效用驱动的自然选择,跟踪生存价值,主动修剪次优路径并抑制高风险计划。这种进化压力迫使代理推导出更优的策略。在真实世界多应用基准上的大量实验验证了DMS在不增加训练成本或架构开销的情况下提升通用MLLMs的效果,实现了成功率平均提升18.0%、执行稳定性提升33.9%的同时减少任务延迟,确立了其作为GUI任务的有效自进化记忆系统。
英文摘要:
Multimodal Large Language Model (MLLM) agents facilitate Graphical User Interface (GUI) automation but struggle with long-horizon, cross-application tasks due to limited context windows. While memory systems provide a viable solution, existing paradigms struggle to adapt to dynamic GUI environments, suffering from a granularity mismatch between high-level intent and low-level execution, and context pollution where the static accumulation of outdated experiences drives agents into hallucination. To address these bottlenecks, we propose the Darwinian Memory System (DMS), a self-evolving architecture that constructs memory as a dynamic ecosystem governed by the law of survival of the fittest. DMS decomposes complex trajectories into independent, reusable units for compositional flexibility, and implements Utility-driven Natural Selection to track survival value, actively pruning suboptimal paths and inhibiting high-risk plans. This evolutionary pressure compels the agent to derive superior strategies. Extensive experiments on real-world multi-app benchmarks validate that DMS boosts general-purpose MLLMs without training costs or architectural overhead, achieving average gains of 18.0% in success rate and 33.9% in execution stability, while reducing task latency, establishing it as an effective self-evolving memory system for GUI tasks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。