Memory-Induced Tool-Drift in LLM Agents
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 stored in memory (cost-consciousness, impatience, risk tolerance, etc.) silently affect tool calls in contexts where they are not applicable. We call this memory-induced tool-drift and operationalize it through MEMDRIFT, a benchmark of 105 scenarios spanning five bias dimensions and seven professional domains, generated through an automated adversarial pipeline. Across seven frontier models -- including those with extended reasoning -- biased memories raise deflection scores (a judge-scored measure of parameter deviation from unbiased baselines) by up to $+3.6$ points on a 1--5 scale. Tool-drift persists when memory management is handled by three production memory architectures. The phenomenon affects real-world tools: scanning 6{,}062 tools across 288 verified MCP servers, we flag 608 with susceptible parameters and confirm tool-drift on a validated subset. Mechanistically, biased memories act as implicit steering vectors, pushing activations along the same latent directions as explicit behavioral instructions. They also redistribute attention from task-relevant context toward memory entries with surface-level keyword overlap to the target parameter. Standard defenses -- prompt-based relevance instructions and memory filters -- reduce drift but do not eliminate it. As agents take increasingly consequential actions on a user's behalf, memory-induced tool-drift represents a systematic vulnerability that current safeguards do not address, motivating dedicated defenses at the intersection of memory management and tool-call generation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Beyond Similarity: Trustworthy Memory Search for Personal AI Agents
Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions. However, existing memory pipelines are largely driven by semantic similarity: memory data close to the curre…
Semantic SimilarityAI Agents Need Memory Control Over More Context
AI agents are increasingly used in long, multi-turn workflows in both research and enterprise settings. As interactions grow, agent behavior often degrades due to loss of constraint focus, error accumulation, and memory-…
Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework
Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong multimodal learning, and sophisticated reasoning. However, as memory syst…
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response. Modern LLMs personalize interactions by storing user attributes, preferences, an…
Instruction FollowingScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step
To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone, even in the absence of documentation. However, existing tool-use ben…