Errors in large reasoning models form a forest structure that grows with more steps, making the first solution best; RED refines the first and prunes the rest for higher performance with less compute.
**OUTPUT** 4.0 ### Example 4.0−B (complex propagation: wrong theorem form reused; child has extra arithmetic error) **CONTEXT_UP_TO_CHILD**
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
Errors in large reasoning models form a forest structure that grows with more steps, making the first solution best; RED refines the first and prunes the rest for higher performance with less compute.