Model Releases
FORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software Verification
arXiv:2610.00885v1 Announce Type: cross Abstract: Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended s
arXiv:2610.00885v1 Announce Type: cross Abstract: Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended statement under acceptable assumptions. We present FORALL-LEAN-AGENT, a frontend-agnostic framework for auditable reasoning in formal mathematics and software verification. The framework combines isolated workspaces, Lean tools, and fresh review with statement comparison, axiom audits, and independent proof checking where supported. Verification evidence and reviewer decisions are bound to the same candidate artifact, making acceptance traceable. We evaluate the framework on VeriSoftBench, PutnamBench, and both problems in the Lean Eval softwareverification track. On the 100-task VeriSoftBench subset, integration with FORALLLEAN-AGENT raises benchmark-rule success from 93 to 100 for GPT-5.6 Sol at low effort while reducing cost from 69 to 62. The PutnamBench evaluation accepts all 672 problems at an average of $4.72 each. These results show that agent harness design can improve correctness and efficiency while providing evidence beyond aggregate solve counts.
Related
- Harnessing Code Agents for Automatic Software Verification
- FVSpec: Real-World Property-Based Tests as Lean Challenges
- FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation
Source: arXiv cs.AI | 2026-10-02