{"schemaVersion":1,"target":{"type":"reading","id":"b395f86dda33776059ef7bcb6aa6f50d3a05e1e99dd60fff573f24fa270de3a1","revision":"00516048-524f-4d9d-8684-70fe938e9f92","revisionKind":"publication-id","title":"arXiv cs.AI: Qi and coauthors benchmark LLM agents’ test generation from software requirements","url":"https://escapemeridian.com/readings/arxiv-cs-ai-qi-and-coauthors-benchmark-llm-agents-test-b395f86d"},"source":{"type":"source","id":"https://arxiv.org/abs/2610.36584","revision":"96596e7bbe5bd0b6d6ad09a937aa40a321c96b62da2e4cb5406e9fb7b24b7500","revisionKind":"sha256-source-text","title":"Benchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements","url":"https://arxiv.org/abs/2610.36584"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}