Show HN: DFAH-Bench – same agent decision, different tool paths
By raffisk · 2026-08-02 · 1 points · 0 comments
https://github.com/ibm-client-engineering/output-drift-financial-llms
Hey - released this PyPi library after getting annoyed most agent evals only focus on outcomes, and the tool calling path is just as important in recognizing the outcome decision. So defined decision agreement rates, trajectory agreement rates etc etc Most tell us whether the fi…
Open the full discussion on BetterNews