DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents
Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new task exactly.
ProofPaper ↗
Key points
- To address this dilemma, we propose DeltaReplay, a step-level memory reuse framework that decides how to use existing memory without modifying it.
- We observe that the reusable part of a stored record is determined not by the record itself but by its relation to the new task, mainly through two factors: page-level consistency and action-level generality.
- We therefore store execution trajectories as paths in a transition graph, whose nodes (pages) and edges (actions between pages) capture these two factors.
- On AndroidWorld and SPA-Bench, DeltaReplay improves the task success rate over a base agent with the same backbone by up to 10.3 and 25.0 percentage points, respectively.
Sources (1)
- [1]DeltaReplay: Task-Relative Memory Reuse for Mobile GUI AgentsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 11:12 AM
Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new task exactly.
To address this dilemma, we propose DeltaReplay, a step-level memory reuse framework that decides how to use existing memory without modifying it.
Extractive summary: sentences quoted from the sources.