Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on a wide range of tas
Drex open decision models return probability distributions over user-supplied options without autoregressive decoding, using supervised fine-tuning, RLAF, and consistency losses to improve accuracy, robustness, and latency.
Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on a wide range of tasks. In production, however, they give inconsistent answers, require parsing of outputs, and add cost and latency. Decision models address this: given a question and a set of options supplied by the user, they return a probability distribution over the options without autoregressive decoding. We present Drex, a family of four open decision models with 8B (DLM), 9B (v1.5), 35B with 3B active (v2.0), and 27B (Max) parameters. Each request consists of a state (a document, record, or agent context,…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Towards Foundation Decision Models: Drex was first seen on Hugging Face · Daily papers on Nov 6, 2026. Since then it has appeared in 33 checks on 3 different days. Its best position was #10 of 30, reached on Nov 6, 21:28 UTC. It is #13 right now, holding steady at #13 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 19:28 UTC it is #13, holding steady at #13 over the last 6 checks.
#10 on Hugging Face · Daily papers, on Nov 6, 21:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 6, 2026 and has been on the list on 3 days (33 checks) since.