Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
ACM Computing Surveys , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.
citing papers explorer
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
-
Context Training with Active Information Seeking
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.