AI Agent Papers2026
Assesses mobile planning agents' ability to call tools, plan long-horizon workflows, and coordinate sub-agents in realistic, interactive phone scenarios via a stateful executable sandbox. Covers 13 domains, 212 tools, evidence-based verification, and tests memory, skill usage, permission and runtime constraints.
AI Agent Papers2026
Develops methods to scale agentic AI for sustained, verifiable execution of complex long-horizon work by expanding executable environments and training coordinated agents with a shared execution harness (AgentOS) to maintain state, provenance, and failure recovery.