A 4B-parameter local LLM trained with tool-augmented process-rewarded learning generates STL formulas from natural language at state-of-the-art accuracy on a new bilingual benchmark.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ReasonSTL: Bridging Natural Language and Signal Temporal Logic via Tool-Augmented Process-Rewarded Learning
A 4B-parameter local LLM trained with tool-augmented process-rewarded learning generates STL formulas from natural language at state-of-the-art accuracy on a new bilingual benchmark.