forced per-field routing audit
Rich evidence does not make routing reliable
The LLM router receives deploy-visible evidence cards and chooses among five correction actions. The full 30-setting grid is complete, but oracle-action agreement remains low, motivating abstention rather than forced action selection.
Router summary
Gemma4 five-action grid, 30 settingsThe five-action router is evaluated as a diagnosis of forced action selection. Low oracle-action agreement and action collapse support the shift to abstention.
Tool-audit router
v3 rich evidence grid across crop, protocol, and sample ratioThe tool-audit grid asks the model to override a tool default only when evidence justifies it. Low override is desirable only if the default is already appropriate; here it mostly confirms that the router is cautious rather than reliably corrective.
Crop-protocol summary
median values across five sample ratios| Crop | Protocol | Settings | Cases | Oracle match median | Action collapse median | LLM vs q_agro median |
|---|
Action distribution by setting
selected action shares in the 30-setting grid| Crop | Protocol | SR | Base only | Cal full | q_agro full | Oracle match | Collapse | LLM vs q_agro |
|---|