Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
arXiv 2603.18245•3e8d2da44754c1ea97ed16c803ff8e02163980c7f400d623d604e34f4df7a37d
Claude CodeDirect Preference Optimization (DPO)GitHub CopilotGreen AILLM agent safetyLLM-assisted code reviewRust verificationSQL comment generationSafeAuditSpaceTime ProgrammingVCoT-Benchadversarial PRsautomated theorem provingbenchmark coverageconfirmation biasdebiasingdesign discussion detectionomniscient debugging and tracing tools","BenchBrowser","benchmarrepository miningrule-resistancesoftware supply-chain attackssustainable ML practicestransformer modelsverification chain-of-thoughtvulnerability detection
Paper metadata
- arXiv ID
- 2603.18245
- 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
- 3e8d2da44754c1ea97ed16c803ff8e02163980c7f400d623d604e34f4df7a37d
- Enrichment time
- 2026-03-20T08:51:52Z
- 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.