提出锚点记忆框架，解决长时GUI任务中记忆失效问题
AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
- 用因果关联的中间状态锚点替代完整操作序列
- 在1069个任务上提升任务完成率5%-30.16%
- 适合研究长时交互与记忆机制的AI开发者
长时GUI代理是实现实用部署的关键，但现有范式下有效交互记忆仍缺乏探索。完整重放操作序列冗余且放大噪声，而摘要常丢失依赖关键信息和可追溯性。本文提出AndroTMem，一种针对长时安卓GUI代理的锚点记忆诊断框架。其核心基准AndroTMem-Bench包含1069个任务、34,473个交互步骤（平均每个任务32.1步，最多65步）。通过任务完成率（TCR）评估需传递关键中间状态的任务，该基准强制强步骤间因果依赖，使稀疏但关键的中间状态决定后续动作，聚焦交互记忆评估。在开源与闭源GUI代理中均发现：随着序列变长，性能下降主要由任务内记忆失败驱动，而非孤立感知错误或局部动作失误。基于此诊断，提出锚定状态记忆（ASM），将交互序列表示为一组因果关联的中间状态锚点，支持子目标定向检索与归因感知决策。在多个设置及12个评估代理中，ASM持续优于全序列重放与摘要基线，提升TCR 5%-30.16%，AMS 4.93%-24.66%，表明锚定结构化记忆有效缓解长时任务中的交互记忆瓶颈。代码、基准及相关资源已公开于[https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem)。
原文摘要 · Abstract (English)
Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).
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。