MobilePA-Bench: Benchmark for Mobile Planner Agents
Yi Zhu · hf · 2026-08-25
MobilePA-Bench is an interactive sandbox benchmark for evaluating mobile planner agents. It assesses tool-calling, sub-agent collaboration, memory usage, and composite skill invocation under real runtime constraints.
More from coding & agent
- Tencent Cloud ships ADP 4.0 overseas: full-lifecycle agent development platform — vista8 · 2026-08-25
- Claude Code hits 95.4% cache hit-rate vs Codex's 86.4% across 7,565 agentic coding trials — zainhas · 2026-08-25
- Niels Rogge launches new research tool integrating agent search and Semantic Scholar API — NielsRogge · 2026-08-25
- Hermes Agent Adds Support to Pin OpenRouter Model Providers — Teknium · 2026-08-25
- Switching models constantly invalidates prompt cache and doubles costs — Teknium · 2026-08-25
- Grok Bot autonomously cancels services by handling email login loops — elonmusk · 2026-08-25