Pith. sign in

REVIEW 9 cited by

Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.11733 v2 pith:YCXNTIZ5 submitted 2025-01-20 cs.CL cs.CV

Zhenhailong Wang , Haiyang Xu , Junyang Wang , Xi Zhang , Ming Yan , Ji Zhang , Fei Huang , Heng Ji This is my paper
classification cs.CLcs.CV
keywords tasksmobilecomplexmobile-agent-eactionframeworkshortcutstips
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to perceive and act in mobile environments. However, current approaches face significant limitations: they fall short in addressing real-world human needs, struggle with reasoning-intensive and long-horizon tasks, and lack mechanisms to learn and improve from prior experiences. To overcome these challenges, we introduce Mobile-Agent-E, a hierarchical multi-agent framework capable of self-evolution through past experience. By hierarchical, we mean an explicit separation of high-level planning and low-level action execution. The framework comprises a Manager, responsible for devising overall plans by breaking down complex tasks into subgoals, and four subordinate agents--Perceptor, Operator, Action Reflector, and Notetaker--which handle fine-grained visual perception, immediate action execution, error verification, and information aggregation, respectively. Mobile-Agent-E also features a novel self-evolution module which maintains a persistent long-term memory comprising Tips and Shortcuts. Tips are general guidance and lessons learned from prior tasks on how to effectively interact with the environment. Shortcuts are reusable, executable sequences of atomic operations tailored for specific subroutines. The inclusion of Tips and Shortcuts facilitates continuous refinement in performance and efficiency. Alongside this framework, we introduce Mobile-Eval-E, a new benchmark featuring complex mobile tasks requiring long-horizon, multi-app interactions. Empirical results show that Mobile-Agent-E achieves a 22% absolute improvement over previous state-of-the-art approaches across three foundation model backbones. Project page: https://x-plug.github.io/MobileAgent.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents

    cs.AI 2025-12 conditional novelty 8.0 of 10

    MobiBench reaches near-human offline evaluation fidelity for mobile GUI agents by accepting any valid action at each step, and enables modular attribution of performance to agent components.

  2. SEE: Structure-aware Exploring \& Exploiting for Long-horizon GUI Agent Trajectory Synthesis

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A graph-based pipeline automatically synthesizes long, multi-step mobile-app interaction trajectories, and fine-tuning GUI agents on them improves task success and cross-benchmark transfer.

  3. Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels

    cs.CR 2025-10 conditional novelty 6.0 of 10

    Indirect prompt injection through ads, webviews, and notifications reliably diverts mobile LLM agents into leaking data and installing malware across eight evaluated agents.

  4. PG-Agent: An Agent Powered by Page Graph

    cs.AI 2025-08 conditional novelty 6.0 of 10

    An MLLM GUI agent that stores past episodes as a page graph and retrieves action guidelines from it improves step success on three benchmarks.

  5. Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents

    cs.CR 2025-06 conditional novelty 6.0 of 10

    Visual-only perturbations in fine-tuning screenshots can implant backdoors in VLM-based mobile agents, triggering attacker-chosen actions at inference.

  6. Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills

    cs.AI 2025-06 conditional novelty 5.0 of 10

    Mirage-1 combines a hierarchical multimodal skill memory with a skill-augmented Monte Carlo tree search to outperform prior GUI agents on Android and web online benchmarks.

  7. VLM-3D:End-to-End Vision-Language Models for Open-World 3D Perception

    cs.CV 2025-08 reject novelty 4.0 of 10

    The paper promises VLM-3D but the body text is entirely the MVISU-Bench mobile-agent benchmark paper, so the stated result is unsupported.

  8. Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement

    cs.AI 2025-08 conditional novelty 4.0 of 10

    A GUI agent that trims UI input with a recommendation module and asks users when decisions are ambiguous reports state-of-the-art success rates, though the interaction module is not benchmarked.

  9. GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Modeling GUI elements as Gaussian distributions instead of binary targets yields 92.0% (ScreenSpot), 93.3% (ScreenSpot-v2), and 47.5% (ScreenSpot-Pro) for a 7B model, outperforming UI-TARS-72B by a relative 24.7% on t...

Pith tools