LLM2Cert:以 LLM 合成證書,並透過 SMT/Lean 驗證
LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification
LLM2Cert 是一個以 LLM 驅動的框架,可合成穩定性與安全性證書,並透過 SMT 求解器或 Lean Proof-Repair agent 驗證。研究提出包含 105 個實例的 DynaCertBench,LLM2Cert 成功驗證 81 個,比例為 77.1%,較不帶回饋的一次性提案提高 17.1 個百分點。
Published on Oct 21
Authors:
,
,
,
,
,
,
,
Abstract
A benchmark of nonlinear dynamical systems and an LLM-driven framework that synthesizes and verifies stability and safety certificates via SMT solvers and proof repair agents achieve substantial verification improvements.
Lyapunov functions and barrier certificates give state-space guarantees of stability and safety, but synthesizing and verifying them---especially for nonlinear, high-dimensional systems---remains an open challenge. Existing pipelines verify candidates with numerical solvers (sum-of-squares programs), interval methods, or satisfiability-modulo-theories (SMT) solvers, which often require relaxations, are conservative, or scale poorly with model dimension and nonlinearity. These limitations have also shaped benchmark design: standard test suites are dominated by low-dimensional polynomial systems chosen to suit what solvers can handle rather than what engineering applications require. We address both sides of this challenge. First, we introduce DynaCertBench, a benchmark of 105 instances: 80 non-redundant systems curated from the literature, extended with high-dimensional and control-constrained variants and new nonlinearly coupled systems, comprehensively spanning stability, region-of-attraction, forward-invariance, and safety tasks. Second, we present LLM2Cert, an LLM-driven framework that synthesizes candidate certificates and verifies them against their proof obligations: each obligation is routed to an SMT solver or directly to the Lean Proof-Repair agent. On DynaCertBench, LLM2Cert verifies 81 of 105 instances (77.1%), a 17.1 percentage point improvement over one-shot proposal without feedback. On the 81 fixed certificates, LLM2Cert verifies 22 that All-SMT leaves unresolved. Code and data are available at https://github.com/FormalCert-AI/llm2cert.
View arXiv page View PDF Project page GitHub 1 Add to collection
Get this paper in your agent:
hf papers read 2610.30524
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.30524 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.30524 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.30524 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co