AI RESEARCH
Memory-Induced Tool-Drift in LLM Agents
arXiv CS.LG
•
ArXi:2605.24941v1 Announce Type: cross Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinning contemporary production systems. We study a previously unexamined failure of this combination: when personality-driven biases d in memory (cost-consciousness, impatience, risk tolerance, etc.) silently affect tool calls in contexts where they are not applicable.