A* post-training lifts 1B-3B Llama-3.2 models from near-zero to above DeepSeek-V3.2 accuracy on deductive reasoning while trading off efficiency via process rewards.
Masataro Asai and Alex Fukunaga
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
-
Learning to Reason Efficiently with A* Post-Training
A* post-training lifts 1B-3B Llama-3.2 models from near-zero to above DeepSeek-V3.2 accuracy on deductive reasoning while trading off efficiency via process rewards.