# Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactions

arXiv: https://arxiv.org/abs/2601.04170 · HTML: https://mlsanity.com/paper/2601.04170/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 7 of 7)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Challenges in Deploying Machine Learning: a Survey of Case Studies](https://mlsanity.com/paper/2011.09926/) (2020)

## Built on by (most cited first, 28 of 28)

- [Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents](https://mlsanity.com/paper/2602.22302/) (2026)
- [Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework](https://mlsanity.com/paper/2603.11768/) (2026)
- [Runtime Governance for AI Agents: Policies on Paths](https://mlsanity.com/paper/2603.16586/) (2026)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents](https://mlsanity.com/paper/2605.17830/) (2026)
- [TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering](https://mlsanity.com/paper/2605.05980/) (2026)
- [Exploiting LLM Agent Supply Chains via Payload-less Skills](https://mlsanity.com/paper/2605.14460/) (2026)
- [AI Agents Under EU Law](https://mlsanity.com/paper/2604.04604/) (2026)
- [Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms](https://mlsanity.com/paper/2605.30169/) (2026)
- [LLM-enabled Applications Require System-Level Threat Monitoring](https://mlsanity.com/paper/2602.19844/) (2026)
- [How Much Coordination Gain Is Real? A Paired Noise-Floor Protocol for Multi-Agent LLM Benchmarks](https://mlsanity.com/paper/2606.20695/) (2026)
- [Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems](https://mlsanity.com/paper/2606.21666/) (2026)
- [AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories](https://mlsanity.com/paper/2609.06972/) (2026)
- [Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems](https://mlsanity.com/paper/2603.15690/) (2026)
- [Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents](https://mlsanity.com/paper/2604.24686/) (2026)
- [Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines](https://mlsanity.com/paper/2605.27559/) (2026)
- [FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents](https://mlsanity.com/paper/2606.31522/) (2026)
- [Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems](https://mlsanity.com/paper/2608.10216/) (2026)
- [Toward Measuring Structural Drift in LLM Communication Loops](https://mlsanity.com/paper/2604.13061/) (2026)
- [Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems](https://mlsanity.com/paper/2605.14259/) (2026)
- [Steerability via constraints: a substrate for scalable oversight of coding agents](https://mlsanity.com/paper/2607.02389/) (2026)
- [Beyond Component Testing: Validating Agentic AI Systems](https://mlsanity.com/paper/2607.29405/) (2026)
- [Testing and Evaluation of Agentic AI Systems In Military Command and Control](https://mlsanity.com/paper/2608.20597/) (2026)
- [DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents](https://mlsanity.com/paper/2609.10892/) (2026)
- [Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks](https://mlsanity.com/paper/2609.11018/) (2026)
- [World Model Science: Self-Organized Criticality, Weak Chaos, and Metastable Belief Dynamics in Long-Horizon LLM Agents](https://mlsanity.com/paper/2609.17419/) (2026)
- [Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents](https://mlsanity.com/paper/2609.24755/) (2026)
- [MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification](https://mlsanity.com/paper/2610.17613/) (2026)

## Abstract (arXiv)

Multi-agent Large Language Model (LLM) systems have emerged as powerful architectures for complex task decomposition and collaborative problem-solving. However, their long-term behavioral stability remains largely unexamined. This study introduces the concept of agent drift, defined as the progressive degradation of agent behavior, decision quality, and inter-agent coherence over extended interaction sequences. We present a comprehensive theoretical framework for understanding drift phenomena, proposing three distinct manifestations: semantic drift (progressive deviation from original intent), coordination drift (breakdown in multi-agent consensus mechanisms), and behavioral drift (emergence of unintended strategies). We introduce the Agent Stability Index (ASI), a novel composite metric framework for quantifying drift across twelve dimensions, including response consistency, tool usage patterns, reasoning pathway stability, and inter-agent agreement rates. Through simulation-based analysis and theoretical modeling, we demonstrate how unchecked agent drift can lead to substantial reductions in task completion accuracy and increased human intervention requirements. We propose three mitigation strategies: episodic memory consolidation, drift-aware routing protocols, and adaptive behavioral anchoring. Theoretical analysis suggests these approaches can significantly reduce drift-related errors while maintaining system throughput. This work establishes a foundational methodology for monitoring, measuring, and mitigating agent drift in production agentic AI systems, with direct implications for enterprise deployment reliability and AI safety research.