Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-30 · source-backed
Single-shot prompting produced not one valid coverage-producing verification environment on the paper's benchmarks. AgentDV closes the loop with runnability filtering, CSR-grounded checking to cut hallucinated signals, and coverage-guided iteration against measured gaps. Using Claude Sonnet 4.6 it reaches 100% pass on four design-under-test blocks and 80.9% average across all of them, with 74.5% line and 88.4% branch coverage, against 58.7% and 60.6% average pass rates for Llama and Qwen. (arXiv 2608.27148)
Each link below shares sources, entities, or timing with this story.
Meta released Llama / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Meta released Llama); both cover Llama, Qwen; overlapping topics (against, claude).
AgentDV benchmarked against Qwen / Shared entity: Qwen / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (AgentDV benchmarked against Qwen); both cover Qwen; overlapping topics (against, claude).
Meta released Llama / Shared entities / Earlier coverage
Linked by a graph relationship (Meta released Llama); both cover Llama, Qwen; earlier Llama coverage from 2026-05-01.
Linked by a graph relationship (Meta released Llama); both cover Llama, Qwen; earlier Llama coverage from 2026-04-02.
AgentDV benchmarked against Qwen / Shared entity: Qwen / Shared topic / Earlier coverage
Linked by a graph relationship (AgentDV benchmarked against Qwen); both cover Qwen; overlapping topics (block, claude).
Linked by a graph relationship (AgentDV benchmarked against Qwen); both cover Qwen; overlapping topics (against, environment).
Meta released Llama / Same source domain / Shared topic / Tension
Linked by a graph relationship (Meta released Llama); reported by the same outlet (arxiv.org); overlapping topics (against, coverage).
Meta released Llama / Shared entity: Qwen / Earlier coverage / Tension
Linked by a graph relationship (Meta released Llama); both cover Qwen; earlier Qwen coverage from 2026-08-09.