Challenge: Existing GUI agents for real desktop environments require large amounts of high-quality interaction data, but collecting human demonstrations is expensive.
Approach: They propose a framework that bootstraps scalable desktop supervision from seed demonstrations.
Outcome: Experiments on standard desktop benchmarks show that the framework improves on zero-shot agents and representative synthesis baselines.

Similar Papers

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Copied to clipboard

Challenge: Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach: They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome: The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.
GTA: Generating Long-horizon Tasks for Web Agents at Scale (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks provide only coarse start–goal annotations without intermediate trajectories . Existing frameworks provide no supervision over the agent's latent decision process .
Approach: They propose a framework that integrates crawling, retrieval-based seeding, in-context generation and automated quality control to produce realistic tasks paired with executable trajectories.
Outcome: The proposed framework decouples crawling from generation for greater efficiency and ensures dense supervision through deterministic replays and systematic validation.
GUI Agents: A Survey (2025.findings-acl)

Copied to clipboard

Challenge: Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life.
Approach: They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities.
Outcome: The proposed framework delineates their perception, reasoning, planning, and acting capabilities.
From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation (2026.acl-long)

Copied to clipboard

Challenge: Vision-language models are increasingly deployed as computer-use agents that operate desktops and browsers.
Approach: They propose a method that turns static expert traces into policy-aligned guidance . they propose RLVR with a per-task, dynamically updated cache to decompose planning and execution .
Outcome: The proposed model improves UITARS1.5-7B success from 22.87% to 32.13% on OSWorld-Verified and raises a held-out split from 5.74% to 10.30% on MMBench-GUI and Online-Mind2Web.
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents (2024.acl-long)

Copied to clipboard

Challenge: Existing GUI agents interact with the environment through extracted structured data, which can be notably lengthy (e.g., HTML) and occasionally inaccessible (e-book).
Approach: They propose to enhance SeeClick with GUI grounding pre-training and devise a method to automate curation of GUI ground data.
Outcome: The proposed agent improves ScreenSpot, the first realistic GUI grounding benchmark that encompasses mobile, desktop, and web environments.
NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks (2026.acl-long)

Copied to clipboard

Challenge: Current research faces an "Evaluation-Realism Dilemma" due to unstable MLLM judges or manual verification.
Approach: They propose a verifiable evaluation dataset grounded in real-world human GUI intents.
Outcome: The proposed framework outperforms the state-of-the-art framework in achieving a weighted pathway success rate of 45.6% while reducing token consumption and execution time by 76%.
Do GUI Grounders Truly Understand UI Elements? (2026.findings-eacl)

Copied to clipboard

Challenge: Existing grounding models and benchmarks are skewed toward web and mobile environments, neglecting desktop interfaces (especially windows).
Approach: They propose a GUI Grounding Sensitivity Benchmark to assess UI grounding sensitivity to multiple descriptions of the same UI element.
Outcome: The proposed model generates multiple valid instructions per UI element and develops nuanced validation methods to validate them.
AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies focus on specialized agents designed for particular tasks.
Approach: They propose to scale annotated interaction trajectories and fine-tune LLMs on AgentBank to get a series of agent models, Samoyed.
Outcome: The proposed model can scale to get generalized agent capabilities.
Aria-UI: Visual Grounding for GUI Instructions (2025.findings-acl)

Copied to clipboard

Challenge: Using a multimodal model, GUI agents can ground from language instructions to target elements . relying on HTML or AXTree inputs is a challenge for GUI agents .
Approach: They propose a large multimodal model specifically designed for GUI grounding that adopts a pure vision approach instead of auxiliary inputs.
Outcome: The proposed model outperforms vision-only and AXTree-reliant models on offline and online agents.
ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering (2026.acl-long)

Copied to clipboard

Challenge: Real estate agents are labor-intensive, difficult to scale, and prone to interest-driven bias.
Approach: They propose a large-scale benchmark of 29,270 real-estate instances with machine-verifiable supervision for intermediate steps . they propose 'hIRE-Agent' framework that integrates heterogeneous evidence into an understand–plan–execute architecture as a strong baseline .
Outcome: Experiments show that HIRE-Agent integrates heterogeneous evidence . the framework is able to integrate a front-end parser, planning Supervisor, and execution Specialists .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations