A staged tree-of-thought framework called T3 raises LLM-based automated program repair success rates by about 10 to 12 percentage points over chain-of-thought prompting on the MODIT B2Fs and B2Fm benchmarks.
Nmt vs mlm: Which is the best paradigm for apr?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models
A staged tree-of-thought framework called T3 raises LLM-based automated program repair success rates by about 10 to 12 percentage points over chain-of-thought prompting on the MODIT B2Fs and B2Fm benchmarks.