Pith. sign in

REVIEW 8 cited by

AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation

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 2412.18116 v3 pith:P67FOEU5 submitted 2024-12-24 cs.AI

Hao Wen , Shizuo Tian , Borislav Pavlov , Wenjie Du , Yixuan Li , Ge Chang , Shanhui Zhao , Jiacheng Liu
show 3 more authors
Yunxin Liu Ya-Qin Zhang Yuanchun Li
This is my paper
classification cs.AI
keywords codeagentslanguagemobiletaskautomationmodelstasks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have brought exciting new advances to mobile UI agents, a long-standing research field that aims to complete arbitrary natural language tasks through mobile UI interactions. However, existing UI agents usually demand powerful large language models that are difficult to be deployed locally on end-users' devices, raising huge concerns about user privacy and centralized serving cost. Inspired by the remarkable coding abilities of recent small language models (SLMs), we propose to convert the UI task automation problem to a code generation problem, which can be effectively solved by an on-device SLM and efficiently executed with an on-device code interpreter. Unlike normal coding tasks that can be extensively pre-trained with public datasets, generating UI automation code is challenging due to the diversity, complexity, and variability of target apps. Therefore, we adopt a document-centered approach that automatically builds fine-grained API documentation for each app and generates diverse task samples based on this documentation. By guiding the agent with the synthetic documents and task samples, it learns to generate precise and efficient scripts to complete unseen tasks. Based on detailed comparisons with state-of-the-art mobile UI agents, our approach effectively improves the mobile task automation with significantly higher success rates and lower latency/token consumption. Code is open-sourced at https://github.com/MobileLLM/AutoDroid-V2.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

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

    cs.AI 2025-12 accept novelty 8.0 of 10

    MobiBench is the first modular multi-path offline benchmark for mobile GUI agents, achieving 94.72% agreement with human evaluators while allowing component-level analysis.

  2. Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference

    cs.AR 2026-07 conditional novelty 7.0 of 10

    Cross-layer measurements of five mobile LLM frameworks on CPU/GPU/NPU reveal amplified NPU framework gaps, a prefill–decode backend phase split, and up to ~55% NPU energy savings from scheduling fixes.

  3. MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

    cs.AI 2025-09 conditional novelty 7.0 of 10

    MAS-Bench introduces 139 tasks, 88 predefined shortcuts, and 9 metrics to evaluate hybrid GUI-shortcut mobile agents, reporting up to 68.3% success and 39% efficiency gains over GUI-only baselines.

  4. AgentLens: Adaptive Visual Modalities for Human-Agent Interaction in Mobile GUI Agents

    cs.HC 2026-04 unverdicted novelty 6.0 of 10

    AgentLens adaptively deploys Full UI, Partial UI, and GenUI modalities with virtual display overlays for mobile GUI agents, yielding 85.7% user preference and best-in-study usability in a 21-participant evaluation.

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

    cs.AI 2025-12 conditional novelty 6.0 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.

  6. Mobile GUI Agents under Real-world Threats: Are We There Yet?

    cs.CR 2025-07 conditional novelty 6.0 of 10

    Introduces an app-content instrumentation framework and benchmark showing that examined GUI agents suffer 42.0% and 36.1% average misleading rates from third-party content in dynamic and static tests respectively.

  7. iPanda: An LLM-based Agent for Automated Conformance Testing of Communication Protocols

    cs.SE 2025-07 conditional novelty 6.0 of 10

    An LLM-based agent that parses protocol RFCs into test cases, synthesizes executable test programs with RAG and chain-of-thought, and iteratively debugs them, reports 4.7x to 10.8x Pass@1 improvements over a pure-LLM ...

  8. 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.

Pith tools