# DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents

arXiv: https://arxiv.org/abs/2610.11707 · HTML: https://mlsanity.com/paper/2610.11707/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 49 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 23 of 23)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents](https://mlsanity.com/paper/2602.16855/) (2026)
- [AppAgent v2: Advanced Agent for Flexible Mobile Interactions](https://mlsanity.com/paper/2408.11824/) (2024)
- [AppAgentX: Evolving GUI Agents as Proficient Smartphone Users](https://mlsanity.com/paper/2503.02268/) (2025)
- [Get Experience from Practice: LLM Agents with Record & Replay](https://mlsanity.com/paper/2505.17716/) (2025)
- [MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments](https://mlsanity.com/paper/2602.06075/) (2026)
- [UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents](https://mlsanity.com/paper/2602.05832/) (2026)
- [MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation](https://mlsanity.com/paper/2507.21953/) (2025)
- [Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution](https://mlsanity.com/paper/2601.22528/) (2026)
- [Enhancing Web Agents with a Hierarchical Memory Tree](https://mlsanity.com/paper/2603.07024/) (2026)
- [Executable Agentic Memory for GUI Agent](https://mlsanity.com/paper/2605.12294/) (2026)
- [SE-GA: Memory-Augmented Self-Evolution for GUI Agents](https://mlsanity.com/paper/2605.16883/) (2026)
- [UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents](https://mlsanity.com/paper/2605.29534/) (2026)
- [Mem-W: Latent Memory-Native GUI Agents](https://mlsanity.com/paper/2605.09317/) (2026)
- [Beyond Training: Enabling Self-Evolution of Agents with MOBIMEM](https://mlsanity.com/paper/2512.15784/) (2025)
- [FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory](https://mlsanity.com/paper/2608.04530/) (2026)
- [ActionEngine: From Reactive to Programmatic GUI Agents via State Machine Memory](https://mlsanity.com/paper/2602.20502/) (2026)
- [Rethinking Experience Utilization in Self-Evolving Language Model Agents](https://mlsanity.com/paper/2605.07164/) (2026)
- [EchoPath: Execution-Level Replayable Memory for GUI Agents](https://mlsanity.com/paper/2609.16635/) (2026)

## Abstract (arXiv)

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. The new task may use different parameters, share only some of its steps with a stored trajectory, or have no relevant record in memory. Forcing the agent to use irrelevant memory can mislead it, whereas discarding memory that may still be useful deprives it of guidance from past experience. 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. At reuse time, the action on each edge is split into a task-independent operation and task-specific parameters. DeltaReplay then compares each recorded step with the new task and the current screen, and decides whether to follow it, execute it after replacing its parameters, or leave it to the base agent. 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. These results indicate that deciding at each step how to use retrieved memory lets agents benefit even from partially matching trajectories.