Agentic Knowledgeable Self-awareness
- Published
- Source
- arXiv
- Paper number
- 058
- Field
- Agents / Self-Awareness
- arXiv ID
- 2504.03553
Key points
- Current LLM agents lack situational self-awareness, so they use cognitive resources such as reflection and external knowledge in a scattered and inefficient way.
- Existing agent training methods are vulnerable to unexpected signals, prone to pattern collapse, and often incur high reasoning costs because they rely on a one-size-fits-all approach.
- Agents also struggle to assess their own abilities dynamically in complex and changing environments, which leads to suboptimal decisions.
- KnowSelf introduces a three-stage situational classification scheme, Fast, Slow, and Knowledgeable Thinking, to determine an agent's real-time cognitive resource needs.
- It builds a lightweight offline knowledge system and generates self-awareness data by appending special tokens that indicate the type of thinking required for the trajectories the agent explored.
- A two-stage fine-tuning process, SFT and RPO, teaches agents to connect situational cues with the right cognitive response, enabling them to activate reflection or external knowledge dynamically during inference.
Paper links
External research summaries. These are not HDATF publications or measured product results.