Contextual Agentic Memory is a Memo, Not True Memory
- Published
- Source
- arXiv
- Paper number
- 177
- Field
- Agents / Memory
- arXiv ID
- 2604.27707
Key points
- Current LLM agent memory mainly relies on external lookup mechanisms, and that is often mistakenly treated as the same thing as true learning and expertise development.
- Lookup-based agents do not generalize effectively to novel tasks that require composition, and they only accumulate information without developing internal knowledge.
- Existing agent memory structures are vulnerable to persistent security breaches because temporary prompt injections can be stored and retrieved permanently.
- This paper redefines memory for LLM agents by distinguishing case-based lookup, which is context engineering, from rule-based weight-encoded learning, which is theta-learning.
- It formalizes the limitations of lookup-based memory as a theorem on the generalization gap for compositional tasks.
- It proposes a coexistence architecture that combines fast episodic lookup with a unified channel that periodically encodes distilled experience into model weights offline.
Paper links
External research summaries. These are not HDATF publications or measured product results.