[milkkarten]

These are the marginal tax rates not the effective tax rate (e.g. 80% of first $10k, 30% of $10k-20k). We do not model tax credits here. We try to keep the system as simple as possible so that we can effectively evaluate changes. As is, the Economic theory is intractable once we introduce bounded rationality from purely rational. We do think in future work we can potentially work out some smoothness in the overall tax rate but try to let the LLM planner try what it thinks is best in order to help test the in-context optimization capabilities.

Also, while there is a complicated tax code in the US, in our simulation there is no way for agents to avoid paying taxes :)

The Saez tax rates are perturbed from the LLM Economist's tax rates to find the theoretically optimal values according to the economic theory.

Thanks for the interest and I hope that this helps clarify some of the details.

[slwvx]

Thanks for the further details!

Ah, the fact that they are marginal rates makes marginally more sense, but it still seems to me that the SWF in fig 5a has very little relation to the real world.

> Also, while there is a complicated tax code in the US, in our simulation there is no way for agents to avoid paying taxes :)

Seems like an obvious thing to add. I.e. if you believe the World Bank when they say "People are more willing to pay tax when taxes are progressive" [1], then it seems worthwhile to update your model to include this.

[1] https://blogs.worldbank.org/en/governance/why-does-progressi...