# NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks

arXiv: https://arxiv.org/abs/2508.01330 · HTML: https://mlsanity.com/paper/2508.01330/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 2 Aug 2025.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [Evaluation and Benchmarking of LLM Agents: A Survey](https://mlsanity.com/paper/2507.21504/) (2025)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials](https://mlsanity.com/paper/2412.09605/) (2024)
- [AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories](https://mlsanity.com/paper/2504.08942/) (2025)
- [ScreenAgent: A Vision Language Model-driven Computer Control Agent](https://mlsanity.com/paper/2402.07945/) (2024)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models](https://mlsanity.com/paper/2403.04811/) (2024)
- [JuStRank: Benchmarking LLM Judges for System Ranking](https://mlsanity.com/paper/2412.09569/) (2024)
- [RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users](https://mlsanity.com/paper/2504.10445/) (2025)
- [Efficient Agent Training for Computer Use](https://mlsanity.com/paper/2505.13909/) (2025)
- [NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains](https://mlsanity.com/paper/2503.00870/) (2025)
- [PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World](https://mlsanity.com/paper/2412.17589/) (2024)
- [BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin](https://mlsanity.com/paper/2403.07354/) (2024)

## Built on by (most cited first, 2 of 2)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Rethinking Agentic Reinforcement Learning In Large Language Models](https://mlsanity.com/paper/2604.27859/) (2026)

## Abstract (arXiv)

Despite significant advances in LLM-driven GUI agents, the field remains constrained by the challenge of reconciling high-fidelity realism with verifiable evaluation accuracy. To address this, we introduce NaturalGAIA, a verifiable evaluation dataset grounded in real-world human GUI interaction intents. By decoupling logical causal pathways from linguistic narratives, it rigorously simulates natural human intent, characterized by cognitive non-linearity and contextual dependencies. Furthermore, we propose LightManus-Jarvis, a hierarchical collaborative framework where LightManus manages dynamic topological planning and context evolution, while Jarvis~ensures execution precision via hybrid visual-structural perception. Experiments demonstrate that our approach achieves a Weighted Pathway Success Rate of 45.6%, significantly outperforming the state-of-the-art baseline (21.1%), while reducing token consumption by 75% and execution time by 76%. These results validate the efficacy of the macro-planning and micro-execution paradigm in handling complex naturalized tasks. Our code is publicly available at: https://github.com/KeLes-Coding/NatureGAIA.