Verifier-backed committee search boosts a weak reasoning model from 67% to 76.4% on SWE-bench Verified, matching stronger models by using local soundness signals to select among proposals.
Chen, Neel Guha, Christopher Ré, and Azalia Mirhoseini
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
-
Agentic Systems as Boosting Weak Reasoning Models
Verifier-backed committee search boosts a weak reasoning model from 67% to 76.4% on SWE-bench Verified, matching stronger models by using local soundness signals to select among proposals.