Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
Hongming Zhang, Xiaoman Pan, Hongwei Wang, Kaixin Ma, Wenhao Yu, Dong, Yu

TL;DR
Cognitive Kernel is an open-source, model-centric agent system designed for autonomous, generalist autopilots that actively gather information and make decisions, outperforming or matching existing systems in various scenarios.
Contribution
It introduces a flexible, environment-agnostic design for autopilot systems using a central LLM policy, enabling active information acquisition and decision-making.
Findings
Achieves better or comparable performance in real-time info management
Supports private deployment via full dockerization
Demonstrates effectiveness in long-term memory management
Abstract
We introduce Cognitive Kernel, an open-source agent system towards the goal of generalist autopilots. Unlike copilot systems, which primarily rely on users to provide essential state information (e.g., task descriptions) and assist users by answering questions or auto-completing contents, autopilot systems must complete tasks from start to finish independently, which requires the system to acquire the state information from the environments actively. To achieve this, an autopilot system should be capable of understanding user intents, actively gathering necessary information from various real-world sources, and making wise decisions. Cognitive Kernel adopts a model-centric design. In our implementation, the central policy model (a fine-tuned LLM) initiates interactions with the environment using a combination of atomic actions, such as opening files, clicking buttons, saving…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications
MethodsSparse Evolutionary Training
