Back Rohan Paul

Rohan Paul· @rohanpaul_ai · X· 2026-10-23 02:00 · Original publication time AI score54

Google DeepMind paper proposes auctions to choose which AI model answers a questionMachine translation

Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.

AI introduction

When the best model for a new question is unknown in advance, the paper proposes letting models bid for the chance to answer, with the highest bidder taking the question. In simulated auctions among 110 models on more than 30,000 EmbedLLM prompts, this reached 99.2% of the best possible value; the stated use case is a bidding pool with several strong models.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

Rohan Paul@rohanpaul_ai

New Google DeepMind paper shows that if AI models offer money to answer each question and the highest offer answers, results are 99.2% as good as always picking the best model.

i.e. say you don't know in advance which model is best for each new question. So who should answer?

The paper’s answer: let each model offer money for the job. The model that knows it is good at this question offers more. Highest offer gets to answer.

They proved the loss shrinks when several agents usually value a prompt highly, as when distilled models perform close to the best. They simulated auctions among 110 models on over 30,000 EmbedLLM prompts.

With all 110 models bidding, the auction reached 99.2% of the best possible value, versus 89.4% for routing each prompt type to its best model. On each method's worst prompt cluster, the auction held 96.0% while the single best model kept 6.0%.

If you run a model marketplace, a simple pay-your-bid auction works well when every bidding pool has several strong models.

02:00 · 2026-10-23 · UTC+8

Found an error? Send a correction