ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization

arXiv 2605.16299•8985b807213f97f7b7fac53d93915e320d19e6d26ba24386e40111cbd70ff973
AR-testingDevOps-securityGenAI-policyLLMMove-languageSBSEadversarial-examplesadversarial-testingautomated-testingcode-generationdiffusion-modelsempirical-studygovernancehuman-in-the-looplow-codemerge-conflict-resolutionopen-source-contributionsreinforcement-learningself-improving-systemssmart-contractssoftware-repositoriesstatic-analysissupply-chainunit-tests

Paper metadata

arXiv ID
2605.16299
Version
Not specified by this published record
Category
Computer Science — Software Engineering (cs.SE)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_se
Record identifier
8985b807213f97f7b7fac53d93915e320d19e6d26ba24386e40111cbd70ff973
Enrichment time
2026-05-19T08:51:44Z
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.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization · Baitaphish