MAS-Bench introduces 139 tasks, 88 predefined shortcuts, and 9 metrics to evaluate hybrid GUI-shortcut mobile agents, reporting up to 68.3% success and 39% efficiency gains over GUI-only baselines.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Web agents should default to planning a complete task program before observing live web content to reduce prompt injection exposure, since WebArena tasks are compatible and 80% need no runtime LLM calls.
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
MGA is a memory-driven GUI agent that uses an observer for bias-free screen reading and structured memory for compact state transitions to enable efficient long-horizon automation.
ANX introduces a protocol-first design with 3EX architecture that cuts token consumption by 47-66% and execution time by 58% versus prior methods in form-filling tests.
LLM agents enable universal interoperability by serving as automatic translators and adapters between proprietary digital services.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
citing papers explorer
-
MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents
MAS-Bench introduces 139 tasks, 88 predefined shortcuts, and 9 metrics to evaluate hybrid GUI-shortcut mobile agents, reporting up to 68.3% success and 39% efficiency gains over GUI-only baselines.
-
Web Agents Should Adopt the Plan-Then-Execute Paradigm
Web agents should default to planning a complete task program before observing live web content to reduce prompt injection exposure, since WebArena tasks are compatible and 80% need no runtime LLM calls.
-
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
-
MGA: Memory-Driven GUI Agent for Observation-Centric Interaction
MGA is a memory-driven GUI agent that uses an observer for bias-free screen reading and structured memory for compact state transitions to enable efficient long-horizon automation.
-
ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture
ANX introduces a protocol-first design with 3EX architecture that cuts token consumption by 47-66% and execution time by 58% versus prior methods in form-filling tests.
-
LLM Agents Are the Antidote to Walled Gardens
LLM agents enable universal interoperability by serving as automatic translators and adapters between proprietary digital services.
-
Large Language Model-Brained GUI Agents: A Survey
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.