works on
agent loops 1large language models 1repair 1structured feedback 1textworld 1validation 1

From the 1 of 5 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models

Jaideep Ray

Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This paper targets on-device and…