# AI use cases for Qwen Planner Agent (Tongyi-MAI/Qwen-Planner-Agent) Repo: [Tongyi-MAI/Qwen-Planner-Agent](https://github.com/Tongyi-MAI/Qwen-Planner-Agent) | Use cases: 3 | Page: https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/ A blog and technical report website repository for Qwen-Planner-Agent, a mobile planner agent framework, that shows research results and recorded examples but does not release model weights, training code, or the agent implementation. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Cite the Qwen Planner Agent paper in a bibliography: https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/cite-qwen-planner-agent-paper/ - Review recorded planner tool-use traces for agent design: https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/review-planner-tool-use-replays/ - Compare planner systems on MobilePA-Bench by category: https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/compare-mobile-planner-benchmark-scores/ ## How to cite the Qwen Planner Agent paper in a bibliography with Qwen Planner Agent Repo: [Tongyi-MAI/Qwen-Planner-Agent](https://github.com/Tongyi-MAI/Qwen-Planner-Agent) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Add the paper's BibTeX entry to your bibliography and confirm the arXiv link before you cite it. **Who it is for:** A researcher or student writing related work on mobile GUI planner agents who needs a correct citation for Qwen Planner Agent. **The problem:** Citing the paper by hand risks wrong author order, a missing DOI, or a link that does not match the arXiv record. **The outcome:** A verified BibTeX entry with the arXiv ID, DOI, and URL, ready to use in a manuscript. ### Steps 1. Open https://arxiv.org/abs/2609.29892 and confirm the title matches Qwen Planner Agent. 2. Open the README Citation section in the Tongyi-MAI/Qwen-Planner-Agent repository and copy the bibtex block. 3. Paste the block into your .bib file, keeping the key qu2026qwenplanneragent. 4. Check that the eprint, doi, and url fields match the arXiv page. ### Prompt to paste into your agent ```text Using the README of the Tongyi-MAI/Qwen-Planner-Agent repository, extract the BibTeX entry for the paper and insert it into . Output the entry with key qu2026qwenplanneragent. Verify that the arXiv ID 2609.29892 and the DOI 10.48550/arXiv.2609.29892 appear unchanged. ``` ### Caveat The repository is a website and report repo, so the citation is the only paper-level artifact it gives you; no code can be reused from it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/cite-qwen-planner-agent-paper/ ## How to review recorded planner tool-use traces for agent design with Qwen Planner Agent Repo: [Tongyi-MAI/Qwen-Planner-Agent](https://github.com/Tongyi-MAI/Qwen-Planner-Agent) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Study recorded replays of memory, handoff, and recovery behavior to inform a mobile agent design. **Who it is for:** An agent engineer or product designer building a phone automation agent who needs concrete examples of how a planner handles multi-step tasks. **The problem:** Design discussions about planner behavior stay abstract until you see actual tool arguments, returns, and failed attempts. **The outcome:** A short list of observed patterns, such as confirming prerequisites, passing artifacts between sub-agents, and correcting after errors, each tied to a specific replay. ### Steps 1. Open the interactive examples on the project website at https://tongyi-mai.github.io/Qwen-Planner-Agent/#demos. 2. Open the Sub-Agent Coordination example and note when the planner waits for confirmed downloads before handing off filenames. 3. Open the Error Recovery example and record the failed conversion, the alternative tool call, and the final message. 4. Write down each pattern with its replay name so your design notes can cite it. ### Prompt to paste into your agent ```text Using the Tongyi-MAI/Qwen-Planner-Agent project website demos, review the Error Recovery and Sub-Agent Coordination replays and write a summary of with one bullet per observed behavior. Expected output: a bulleted list where each bullet names the replay and the tool result that triggered the behavior. Verify that every bullet cites a replay that exists on the demos page. ``` ### Caveat The replays show recorded runs on the authors' setup, and the repo does not provide the agent code to rerun them. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/review-planner-tool-use-replays/ ## How to compare planner systems on MobilePA-Bench by category with Qwen Planner Agent Repo: [Tongyi-MAI/Qwen-Planner-Agent](https://github.com/Tongyi-MAI/Qwen-Planner-Agent) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Read the Overall and category scores to shortlist planner systems for a phone automation project. **Who it is for:** A product lead or analyst choosing which planner model to evaluate further for a mobile task automation product. **The problem:** A single overall score hides differences in tool use, memory, Skills, and sub-agent coordination. **The outcome:** A shortlist of systems ranked by the category that matters for your use case, with the cost caveat noted. ### Steps 1. Open the Performance section of the README in the Tongyi-MAI/Qwen-Planner-Agent repository. 2. Compare the Overall column with the Tool Use, Memory, Skills, and Sub-agent columns for the systems you care about. 3. Read the footnote that says cost covers output tokens only, excluding input tokens, external tool charges, device execution, and extra Harness processing. 4. Record the systems that lead in your priority category and mark them for a separate evaluation. ### Prompt to paste into your agent ```text Read the Performance table in the README of the Tongyi-MAI/Qwen-Planner-Agent repository and produce a ranked list of systems for . Expected output: a table with system name, the priority score, and the Overall score. Verify that the scores match the README values and that you state the cost exclusions. ``` ### Caveat The scores are the authors' reported results on MobilePA-Bench, and the repo does not include the benchmark or code to reproduce them. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tongyi-mai-qwen-planner-agent/compare-mobile-planner-benchmark-scores/