WideSWE, a new benchmark of 120 cross-repository tasks, shows top coding agents succeed only 42.5% of the time, revealing major gaps in multi-repo coordination.

EVOHARNESSBENCH shows that expanding an agent's tool, skill, or agent harness alone can degrade performance on previously solved tasks, inducing forgetting up to 34.7%.

Frozen weights do not guarantee safe saturation in agentic coding; auditors must monitor scaffold expansion, not just checkpoint freezing.