implementation detail · filed under evaluation
Official task verifier scoring
Artifacts are scored by the task’s separate official verifier rather than by the agent itself.
Also called official separate verifier.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
the artifacts each agent produces are scored by the task's official separate verifier.
usedunclearin GLM-5.3Z.ai
Filed alongside
Other methods under evaluation :: judge.
Agent-as-a-JudgeIndependent quality-inspection agentAgent-as-a-VerifierDecompositional instruction-following judgeDeterministic tool-call verifierGPT-5.5 (medium) judge modelHuman-calibrated LLM-as-a-JudgeLLM autograding with expert validationLLM-as-a-JudgeLLM-based anti-cheating judgmentLLM-based correctness judgingLLM-based external API usage inspectionMandatory agentic judge protocolReward-hack detection judgeRule-based anti-cheat checks