When to Forget: A Memory Governance Primitive
Agent memory systems accumulate experience but currently lack a principled operational metric for memory quality governance -- deciding which memories to trust, suppress, or deprecate as the agent's task distribution shifts. Write-time importance scores are static; dynamic management systems use LLM judgment or structural heuristics rather than outcome feedback. This paper proposes Memory Worth (MW): a two-counter per-memory signal that tracks how often a memory co-occurs with successful versus
Record details
Published: 13 April 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Evaluating Cooperation in LLM Social Groups through Elected Leadership
arXiv · 13 April 2026
Evaluating Plan Compliance in Autonomous Programming Agents
arXiv · 13 April 2026
Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies
arXiv · 13 April 2026
EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems
arXiv · 13 April 2026
Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation
arXiv · 13 April 2026
Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents
arXiv · 14 April 2026
How to cite this record
ethics.ai (13 April 2026), “When to Forget: A Memory Governance Primitive,” evidence record 5918, https://ethics.ai/record/5918 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.