Agent-directed tree search improves LLM performance on Lean formal verification tasks, with context-based orchestration solving more intermediate specs at lower token cost than baseline agents.
In: Clarke, E.M., Voronkov, A
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Contract-based approach with Dafny verifies correctness of every legal instantiation of configurable SRA systems.
RLVR training raises verified Dafny pass rates from 9.7% to 31.1% on a filtered benchmark while a Lean proof scaffold lifts success from 46.2% to 69.2% on a pilot set and solves 7 of 42 prior unsolved tasks.
citing papers explorer
-
Automating Formal Verification with Agent-Guided Tree Search
Agent-directed tree search improves LLM performance on Lean formal verification tasks, with context-based orchestration solving more intermediate specs at lower token cost than baseline agents.
-
Verification of Configurable SRA Systems
Contract-based approach with Dafny verifies correctness of every legal instantiation of configurable SRA systems.