No article text was recorded for this version.
restricted action space
Version 1 of 131 papers34 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Towards Internet-Scale Training For Agents
- Blog: DeepShop: A Benchmark for Deep Research Shopping Agents
- Blog: Reveal-and-Click: A Benchmark for VLM Agents under Hidden GUI Targets
- Blog: Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
- Blog: A Systematic Study of Behavioral Cloning for Scientific Data Annotation
- Blog: Cortical control of a tablet computer by people with paralysis
- Blog: INREACT: An Inspire-Then-Reinforce Training Framework For Multimodal GUI Agent
- Blog: Automatically Discovering, Reporting and Reproducing Android Application Crashes
- Blog: Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
- Blog: AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
- Blog: UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design
- Blog: Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents
- Blog: WebDancer: Towards Autonomous Information Seeking Agency
- Blog: Enhancing Mobile App Bug Reporting via Real-time Understanding of Reproduction Steps
- Blog: Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking
- Blog: MAI-UI
- Blog: DECAF: Detecting and Characterizing Ad Fraud in Mobile Apps
- Blog: OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
- Blog: V2S: A Tool for Translating Video Recordings of Mobile App Usages into Replayable Scenarios
- Blog: Auto-completing Bug Reports for Android Applications
- Blog: SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
- Blog: DrawInAir: A Lightweight Gestural Interface Based on Fingertip Regression
- Blog: Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
- Blog: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
- Blog: Compositional Investigation: Why Reasoning Enables Tool-Using Agents to Fix What They Diagnose
- Blog: AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
- Blog: GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning
- Blog: AppAgent: Multimodal Agents as Smartphone Users
- Blog: Video2Action: Reducing Human Interactions in Action Annotation of App Tutorial Videos
- Blog: Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions
- Blog: Automatic Versus Human Navigation in Information Networks
History & citation
Current · Permanent link
- This direction split from Advancing Action Spaces for Multimodal GUI Agents (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_restricted_action_space_937239f7,
title = {restricted action space},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/restricted-action-space/rdr_937239f780af4a27bfb5b1b9509df590},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_restricted_action_space_937239f7_v1,
title = {restricted action space},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/restricted-action-space/rdr_937239f780af4a27bfb5b1b9509df590/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}