Pith. sign in

REVIEW 19 cited by

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Not yet reviewed by Pith; the record is open.

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 2412.19723 v3 pith:G34JKKB3 submitted 2024-12-27 cs.AI cs.CLcs.CVcs.HC

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

classification cs.AI cs.CLcs.CVcs.HC
keywords dataos-genesistrajectoryagentsqualitysynthesistaskscollecting
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. Despite their utility in advancing digital automation, a critical bottleneck persists: collecting high-quality trajectory data for training. Common practices for collecting such data rely on human supervision or synthetic data generation through executing pre-defined tasks, which are either resource-intensive or unable to guarantee data quality. Moreover, these methods suffer from limited data diversity and significant gaps between synthetic data and real-world environments. To address these challenges, we propose OS-Genesis, a novel GUI data synthesis pipeline that reverses the conventional trajectory collection process. Instead of relying on pre-defined tasks, OS-Genesis enables agents first to perceive environments and perform step-wise interactions, then retrospectively derive high-quality tasks to enable trajectory-level exploration. A trajectory reward model is then employed to ensure the quality of the generated trajectories. We demonstrate that training GUI agents with OS-Genesis significantly improves their performance on highly challenging online benchmarks. In-depth analysis further validates OS-Genesis's efficiency and its superior data quality and diversity compared to existing synthesis methods. Our codes, data, and checkpoints are available at https://qiushisun.github.io/OS-Genesis-Home/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

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

  1. ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

    cs.CL 2026-06 conditional novelty 7.0

    ISE creates 23,132 execution-grounded multi-turn OS agent trajectories via intent simulation and live execution, improving agent performance on ClawEval from 19.3 to 37.7 pass@1 with Qwen3-8B.

  2. FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems

    cs.MA 2026-04 unverdicted novelty 7.0

    FedGUI is the first comprehensive benchmark for federated GUI agents that studies cross-platform, cross-device, cross-OS, and cross-source heterogeneity, with experiments showing performance gains from cross-platform ...

  3. Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations

    cs.CL 2026-07 conditional novelty 6.0

    Relabeling LLM-agent trajectories with all goals actually achieved, plus action masking and reweighting, yields sample-efficient gains over SFT and DPO on ALFWorld, PlanCraft, and WebShop.

  4. ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks

    cs.AI 2026-06 unverdicted novelty 6.0

    ChainWorld builds 347 chains from atomic OSWorld tasks and benchmarks four agents under single-turn and multi-turn protocols, reporting a maximum 31% completion rate with distinct failure profiles.

  5. ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

    cs.CL 2026-06 conditional novelty 6.0

    Execution-grounded multi-turn OS trajectories from 4D intents and a role-locked simulator raise Qwen3-8B ClawEval pass@1 from 19.3 to 37.7, beating GPT-4o and Qwen3-32B.

  6. Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration

    cs.AI 2026-05 unverdicted novelty 6.0

    SCALE introduces three adversarial roles (Selector, Predictor, Judger) and a graph exploration method (SCALE-Hop) to enable MLLM-based web agents to self-discover limitations and improve, backed by the SCALE-20k datas...

  7. UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization

    cs.LG 2026-04 unverdicted novelty 6.0

    UI-Copilot adds a selective copilot for memory and math to GUI agents and trains tool use with separate single-turn and multi-turn optimization, yielding SOTA results on MemGUI-Bench and a 17.1% gain on AndroidWorld.

  8. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

    cs.LG 2026-02 conditional novelty 6.0

    Action-weighted SFT plus KL-regularized GRPO on a curated 81K reasoning dataset lifts open-source GUI agents by 11–22 points on online task-completion benchmarks.

  9. RISK: A Framework for GUI Agents in E-commerce Risk Management

    cs.AI 2025-09 unverdicted novelty 6.0

    RISK introduces a dataset, benchmark, and R1-style RL fine-tuning for GUI agents that achieve 6.8-8.8% offline gains and 70.5% online task success in e-commerce risk management using 7.2% of baseline parameters.

  10. Instruction Agent: Enhancing Agent with Expert Demonstration

    cs.AI 2025-09 conditional novelty 6.0

    With one human demonstration, the Instruction Agent extracts instructions and uses verifier/backtracker modules to execute them, reaching 60% success on 20 previously unsolved OSWorld tasks.

  11. Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training

    cs.AI 2025-06 unverdicted novelty 6.0

    Mobile-R1 introduces a hierarchical three-stage curriculum that combines format alignment, verifiable action feedback, and multi-turn environment training to improve exploration and self-correction in VLM-based mobile...

  12. LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization

    cs.LG 2025-06 unverdicted novelty 6.0

    LPO optimizes GUI agent positional accuracy by combining information entropy for zone selection with a physical-distance reward inside a Group Relative Preference Optimization framework, claiming SOTA results on bench...

  13. ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

    cs.CL 2026-06 conditional novelty 5.5

    Execution-grounded multi-turn OS trajectories from 4D intents and a role-locked simulator lift Qwen3-8B ClawEval pass@1 from 19.3 to 37.7, beating GPT-4o and Qwen3-32B zero-shot.

  14. AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation and Reinforcement Learning

    cs.AI 2026-06 unverdicted novelty 5.0

    AliyunConsoleAgent-32B reaches 63.52% success on a 278-task cloud console benchmark, closing to 1.82pp of frontier models at 92% lower cost via SFT distillation and GRPO RL.

  15. SynthAgent: Adapting Web Agents with Synthetic Supervision

    cs.LG 2025-11 unverdicted novelty 5.0

    SynthAgent uses dual refinement of synthetic tasks and trajectories to produce higher-quality training data that improves web agent adaptation to target environments.

  16. Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning

    cs.CV 2025-10 conditional novelty 5.0

    HyperClick trains GUI grounding models with GRPO to output clicks plus confidence scores, jointly rewarding correct clicks and Brier-calibrated confidence, and reports SOTA accuracy on six of seven benchmarks with bet...

  17. Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory

    cs.AI 2025-10 conditional novelty 5.0

    Branch-and-Browse, a tree-structured web agent with page-level action memory, reports 35.8% success and up to 40.4% less time than the cited Tree Search baseline on WebArena.

  18. A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

    cs.AI 2025-07 accept novelty 4.0

    The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.

  19. From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review

    cs.AI 2025-04 accept novelty 4.0

    A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.