Retrying failed attempts with fresh samples, called retrials without feedback, is a cheap and effective way to boost LLM reasoning, often outperforming complex methods like tree-of-thoughts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
Retrying failed attempts with fresh samples, called retrials without feedback, is a cheap and effective way to boost LLM reasoning, often outperforming complex methods like tree-of-thoughts.