A recursive divide-and-conquer prompting method with LLM-generated sub-problem dependencies outperforms chain-of-thought baselines on two synthetic list tasks at higher difficulty, with lower token and time cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning
A recursive divide-and-conquer prompting method with LLM-generated sub-problem dependencies outperforms chain-of-thought baselines on two synthetic list tasks at higher difficulty, with lower token and time cost.