open-compass/AgentCompass

[EMNLP 2026] AgentCompass is an extensible open-source evaluation infrastructure for systematically assessing LLM/VLM agent capabilities.

语言：Python · GitHub 星标：184 · Fork：38

话题：agent · benchmark-framework · claude-code · codex · evaluation-framework · harness

在 GitHub 上查看原仓库