← Friday, October 16, 2026AgentsPaper

Intern-Decision returns structured choices in one multimodal model pass

huggingface.co by Tong Zhu et al. Editor score 8/10

Intern-Decision evaluates all fields in a JSON decision skeleton in one causal pass; its 4B model reaches 90.02% average accuracy, with 44.16 ms mean latency for a 289-token request on an RTX 4090. Direct decision outputs could cut latency in agent control loops.

What

Intern-Decision is a family of multimodal models that returns structured choices and candidate probabilities from text and optional images.

Method

A complete JSON skeleton places decision placeholders in each field; one causal forward pass evaluates the fields with the model’s native language-model head.

Why it matters

Structured outputs can simplify agent interfaces and avoid latency from generating free-form responses for finite-choice decisions.

Read on huggingface.co → Code · 786 stars

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.