SGDe compiles workflows into deterministic plans for SLMs using teacher critiques as gradients, achieving 99.3% accuracy on GSM-Hard with three examples under PAC bounds.
Graph of thoughts: Solving elaborate problems with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compiling Deterministic Structure into SLM Harnesses
SGDe compiles workflows into deterministic plans for SLMs using teacher critiques as gradients, achieving 99.3% accuracy on GSM-Hard with three examples under PAC bounds.