MarketplaceLLM OrchestrationCognitiveKernel-Pro
CognitiveKernel-Pro
LLM OrchestrationOpen Source AI & Machine Learning

CognitiveKernel-Pro

Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414

Open Source

About

Extra arguments when running ck_pro.ck_main.main: --inference-time-evaluation-method, where you can choose from no_answer and gpt_judge. no_answer simply checks whether the agent have returned anything meaningful, while gpt_judge use the LLM specified by EVALUATOR_LLM to perform evaluation on the trajectory and decide whether there's a need to retry.

Open Source Health

Not enough history
Stars
530
Forks
56
License
Not stated
Last commit
5 months ago
Python

Related Categories