LLM agents complete over 80% of tasks on a new 849-task Rust verification benchmark and over 90% on unfinished human proofs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.OS 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VeruSAGE: A Study of Agent-Based Verification for Rust Systems
LLM agents complete over 80% of tasks on a new 849-task Rust verification benchmark and over 90% on unfinished human proofs.