龙明
Agent评估与CI验证34篇
2026-08-31 04:27:46
Evals & verification资源。整理自 https://github.com/ai-boost/awesome-harness-engineering（Awesome Harness Engineering），由 zdoc.app 中文镜像页面拆分收录。
Demystifying Evals for AI Agen
agent评估验证
promptfoo/promptfoo
agent评估验证
THUDM/AgentBench
agent评估验证
Testing Agent Skills Systemati
agent评估验证
Agent Evaluation Readiness Che
agent评估验证
Evaluating Skills
agent评估验证
AgentAssay: Token-Efficient Re
agent评估验证
Agentic Harness for Real-World
agent评估验证
Eval-Driven Development: Build
agent评估验证
Agent Evaluation Framework 202
agent评估验证
The 2025 AI Agent Index: Docum
agent评估验证
sentrux/sentrux
agent评估验证
Driving the Agent Quality Flyw
agent评估验证
vaquarkhan/mcp-test-harness
agent评估验证
confident-ai/deepeval
agent评估验证
claw-eval/claw-eval
agent评估验证
SWE-bench
agent评估验证
Accio-org/RealReplicaBench
agent评估验证
UKGovernmentBEIS/inspect_ai
agent评估验证
Quantifying Infrastructure Noi
agent评估验证
AgentLens: Revealing The Lucky
agent评估验证
StaminaBench: Stress-Testing C
agent评估验证
Harness-Bench: Measuring Harne
agent评估验证
sierra-research/tau-bench
agent评估验证
Towards a Science of AI Agent
agent评估验证
Characterizing Faults in Agent
agent评估验证
VeRO: An Evaluation Harness fo
agent评估验证
Eval Awareness in Claude Opus
agent评估验证
Designing AI-Resistant Technic
agent评估验证
Amazon Bedrock AgentCore Evalu
agent评估验证
Live-SWE-agent: First Live Sof
agent评估验证
OccuBench: Evaluating AI Agent
agent评估验证
microsoft/STATE-Bench
agent评估验证
评论
暂无评论，快来发表第一条评论吧