Curriculum proof repair with learned counterexamples
cs.PL, cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/Etha-Sun/Topoverus
Terminology
Sources
- A benchmark for vericoding: formally verified program synthesis
- Qwen3-Coder-Next Technical Report
- Evaluating Large Language Models Trained on Code
- CWM: An Open-Weights LLM for Research on Code Generation with World Models
- SpecRL: Reinforcement Learning with Test-Based Completeness Rewards for Formal Specification Synthesis
- GPT-4o System Card
- Finding Inductive Loop Invariants using Large Language Models
- Learning to Disprove: Formal Counterexample Generation with Large Language Models
- P cubed: Joint Program-and-Proof Planning for Verified Code Generation
- RLTF: Reinforcement Learning from Unit Test Feedback
- DafnyBench: A Benchmark for Formal Software Verification
- Generative Language Modeling for Automated Theorem Proving
- Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
- VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus
- Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
- DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
- ExVerus: Verus Proof Repair via Counterexample Reasoning
- Vero: Can AI Agents Build Formally Verified Software Repositories?
- SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
- RAG-Verus: Repository-Level Program Verification with LLMs using Retrieval Augmented Generation
Related papers
- The Best of Times, the Worst of Times: Moment-Based Analysis of Probabilistic Cost Structures
- Formal Verification of an Out-of-Order Multiprocessor against an In-Order Weak-Memory ISA
- Fuss-free cumulative universes: theory and practice
- High-Level Synthesis of Efficient Pipelines with Visibility Control
- Model Checking Probabilistic Multiparty Session Types
- A Type System for Communication-Safe Hardware Design