From Verification Failures to Reusable Guidance for Coding Agents
cs.SE, cs.AI, cs.LO, cs.PL
Submitted: 2026-09-30
Updated: 2026-10-07
Terminology
Sources
- AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
- Evaluating Large Language Models Trained on Code
- Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?
- DafnyBench: A Benchmark for Formal Software Verification
- SpecGen: Automated Generation of Formal Program Specifications via Large Language Models
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
- LLMs Lean on Priors, Not Programming Language Semantics
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Agent Workflow Memory
- Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification
- Lemur: Integrating Large Language Models in Automated Program Verification
- VERINA: Benchmarking Verifiable Code Generation
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- ExpeL: LLM Agents Are Experiential Learners
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties