From Obligation to Specification: A Survey on Validating EU AI Act Requirements in RE
2026-07-27T08:51:39Z•61ad0d0b55b1783e6a3a31219193ffa990790bb91308abca4e069e2fff75faa1
AI securityC securityCodeQLEU AI ActHugging FaceKLEELLM-generated codeRAGcoding agentscompiler feedbackembedded systemsmodel governancemodel lineagerequirements engineeringsecure code generationsoftware supply chainstatic analysissymbolic executiontraceabilityvibe codingvulnerability discovery
What happened
This collection of arXiv papers examines security, reliability, governance, and operational risks in AI-assisted software development and model supply chains. Key findings include high baseline vulnerability and compilation-error rates in LLM-generated C code, improved results from iterative compiler, static-analysis, symbolic-execution, and retrieval-guided repair, and enhanced vulnerability discovery using LLM-guided symbolic execution. Other papers address governance and traceability gaps under the EU AI Act, uncertain safeguards for “vibe coding,” model-dependent code-review and output-格式️
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_cs_se
- Record identifier
- 61ad0d0b55b1783e6a3a31219193ffa990790bb91308abca4e069e2fff75faa1
- Enrichment time
- 2026-07-27T08:51:39Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.