Apodex 1.1 introduces a framework for "working capability," enabling language models to sustain verifiable progress on complex objectives through file interaction, code execution, and state maintenance. The system achieves this by expanding executable environments and training agents to decompose long-horizon tasks, delegate parallel work, and replan using a shared execution harness called AgentOS.
- Environment Scaling increases the diversity and verifiability of executable file, search, and code environments.
- Agentic Coordination Scaling trains agents to handle task decomposition, parallel delegation, and asynchronous result integration.
- The 35B-parameter Apodex 1.1 Mini provides a locally deployable version that retains strong working capability.
- The model reaches leading performance bands in finance, scientific research, mathematics, coding, and search despite using fewer parameters than many frontier systems.
These results ground agentic intelligence in useful work completed over time, advancing the goal of building a "Heavy-Duty Solver" for ambitious, long-running tasks.