DigiData: Training and Evaluating General-Purpose Mobile Control Agents

Kari Jaaskelainen

11 Nov 2025 — 1 min read

Meet DigiData: AI that can use your phone

Imagine an assistant that taps, swipes, and navigates apps to finish tasks for you. This paper introduces DigiData—a large, diverse, multi-modal dataset built to train mobile control agents to do exactly that.

Richer goals: Instead of scraping random user logs, DigiData maps app features through systematic exploration, yielding harder, more human-relevant tasks.
Real-world testing: DigiData-Bench evaluates agents on complex mobile workflows, not toy demos.
Better metrics: The popular “step accuracy” score can mislead. The authors propose dynamic protocols and AI-powered reviews that judge whether an agent actually completes the task.

Why it matters: Stronger data and fairer evaluations speed up progress toward trustworthy, helpful phone agents—and safer automation of everyday digital chores.

Paper: http://arxiv.org/abs/2511.07413v1

Paper: http://arxiv.org/abs/2511.07413v1

Register: https://www.AiFeta.com

#AI #Mobile #Agents #Dataset #Benchmark #MachineLearning #HCI #UX #Evaluation #MobileAI

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

Meet DigiData: AI that can use your phone

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)