VeriBase: Automated Construction of Theorem Libraries for Software Verification
cs.SE
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/zzhisthebest/Veribase
License: http://creativecommons.org/licenses/by/4.0/
The gist: Software verification is typically more challenging than coding.
Terminology
Abstract
Software verification is typically more challenging than coding. Software developers routinely build on mature libraries and APIs, but turning successful verification solutions into reusable libraries still requires substantial expert effort. In this paper, we propose VeriBase, a framework for automatically constructing software-verification libraries by jointly generalizing code and its associated theorems from successful verification solutions. The key challenge is to generalize implementations together with the theorem statements and proofs that depend on these implementations, and reconcile overlapping components across verification tasks. To this end, VeriBase treats code and its associated theorems as declaration families, and designs a three-phase pipeline, which proves seed tasks, generalizes code and associated theorems, and harvests the resulting families into shared interfaces. VeriBase updates dependent declarations as interface change and uses Lean to check the resulting code and proofs. We evaluate VeriBase across four benchmarks with three backend LLMs. The results show that the general-purpose library built from independent 4,191 programs increases the average task success rate by up to 17.0% and meanwhile reduces the proof completion time by up to 21.4%. When VeriBase constructs a benchmark-specific library, further improvement can be observed.
Sources
- OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
- CSLib: The Lean Computer Science Library
- LLM Library Learning Fails: A LEGO-Prover Case Study
- Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
- GLM-5: from Vibe Coding to Agentic Engineering
- Measuring Coding Challenge Competence With APPS
- Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
- An In-Context Learning Agent for Formal Theorem-Proving
- VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
- DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
- VeriSoftBench: Repository-Scale Formal Verification Benchmarks for Lean
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- VERINA: Benchmarking Verifiable Code Generation
- Planning to Hammer: Difficulty-Aware Decomposition for Automating Rocq Proofs
- DreamProver: Evolving Transferable Lemma Libraries via a Wake-Sleep Theorem-Proving Agent
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters