RESEARCH · RESEARCH · #2336
Navalia framework uses verifiable task synthesis and long-horizon post-training to improve Cowork Agents
Navalia is a framework that builds verifiable analytical tasks from corporate financial reports and applies long-horizon post-training (SFT and RL) to improve Cowork Agent performance. Initialized from Qwen3.6-35B-A3B, the approach uses semantic evidence selection, executable computation chains, and independent verification to generate training trajectories and yields consistent gains across five benchmarks (OfficeQA Pro, FinSearchComp, Finance Agent Benchmark, APEX-Agents-AA, Workspace-Bench-Lite).
KEY POINTS
- Navalia is a framework that builds verifiable analytical tasks from corporate financial reports and applies long-horizon post-training (SFT and RL) to improve Cowork Agent performance.
- Initialized from Qwen3.6-35B-A3B, the approach uses semantic evidence selection, executable computation chains, and independent verification to generate training trajectories and yields consistent gains across five benchmarks (OfficeQA Pro, FinSearchComp, Finance Agent Benchmark, APEX-Agents-AA, Workspace-Bench-Lite).
- Navalia shows a practical pipeline to create verifiable, data-dependent tasks and use them to materially improve long-horizon agent reasoning and tool use, which is important for reliable financial and office automation.
WHY IT MATTERS
Navalia shows a practical pipeline to create verifiable, data-dependent tasks and use them to materially improve long-horizon agent reasoning and tool use, which is important for reliable financial and office automation.