RACES recursively composes 300 verifiable environments using SEQUENTIAL, PARALLEL, SORT, and SELECT operators to boost LLM reasoning on unseen benchmarks, matching full-scale training performance with only 50 base environments.
L ogic P ro: Improving Complex Logical Reasoning via Program-Guided Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
RACES recursively composes 300 verifiable environments using SEQUENTIAL, PARALLEL, SORT, and SELECT operators to boost LLM reasoning on unseen benchmarks, matching full-scale training performance with only 50 base environments.