CCTest · Blog
HarnessDev Tests Whether LLMs Can Build and Evolve Agent Harnesses
AI Agents
cctest.ai
AI Agents

HarnessDev Tests Whether LLMs Can Build and Evolve Agent Harnesses

HarnessDev moves agent evaluation beyond task answers to the runnable infrastructure that shapes those answers. Its results show promising but uneven progress: model-built harnesses still trail mature human systems in coding, search, and research, while performing competitively in writing and machine-learning experiments.

Read more
CCTest · Blog
A New Protocol Tests Whether Agents Fail from Ignorance or Incompetence
Evaluation & Benchmarks
cctest.ai

A New Protocol Tests Whether Agents Fail from Ignorance or Incompetence

A new study proposes knowledge-gated task construction to separate failures caused by missing domain knowledge from failures caused by weak execution or reasoning. Its experiments show a clear artifact-dependent effect on some tasks, while stopping short of claiming any post-training benefit.

Read more
CCTest · Blog
SolarWM Builds Open Infrastructure for Long-Horizon Video World Models
World Models
cctest.ai
World Models

SolarWM Builds Open Infrastructure for Long-Horizon Video World Models

SolarWM addresses a central bottleneck in video world-model research: the disconnect between heterogeneous data, incompatible video backbones, and long-horizon interactive inference. Its unified data contract and three-stage training recipe are designed to turn short training clips into sustained causal rollouts.

Read more