Extending Reasoning in Typed Decision Models via Adaptive Looping

David Berghaus, Arber Zela, Behzad Shomali, Markus Frey, Mehdi Ali, Rafet Sifa, Volkan Cevher

Repeats a shared middle block before scoring answer options, using smaller residual updates when the loop budget grows. Trains one model across several budgets and learns a request-level rule for choosing the amount of computation.

First public: November 5, 2026 · Added to this list: November 9, 2026

Earlier title: Extending Reasoning in Typed Decision Models via Looping.