AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents

• URL: http://arxiv.org/abs/2506.04018v2
• Date: Wed, 01 Oct 2025 15:15:52 GMT
• Title: AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
• Authors: Akshat Naik, Patrick Quinn, Guillermo Bosch, Emma Gouné, Francisco Javier Campos Zabala, Jason Ross Brown, Edward James Young,
• Abstract summary: Large Language Model (LLM) agents become more widespread, associated misalignment risks increase.<n>In this work, we approach misalignment as a conflict between the internal goals pursued by the model and the goals intended by its deployer.<n>We introduce a misalignment propensity benchmark, textscAgentMisalignment, a benchmark suite designed to evaluate the propensity of LLM agents to misalign in realistic scenarios.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely agents are to spontaneously pursue unintended goals in realistic deployments. In this work, we approach misalignment as a conflict between the internal goals pursued by the model and the goals intended by its deployer. We introduce a misalignment propensity benchmark, \textsc{AgentMisalignment}, a benchmark suite designed to evaluate the propensity of LLM agents to misalign in realistic scenarios. Evaluations cover behaviours such as avoiding oversight, resisting shutdown, sandbagging, and power-seeking. Testing frontier models, we find that more capable agents tend to exhibit higher misalignment on average. We also systematically vary agent personalities through different system prompts and observe that persona characteristics can strongly and unpredictably influence misalignment, sometimes more than the choice of model itself. Our results reveal the limitations of current alignment methods for autonomous LLM agents and underscore the need to rethink misalignment in realistic deployment settings.

Related papers

• Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs [0.0]
  Openweight Large Language Models (LLMs) have democratized agentic AI, yet finetuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance.<n>This creates a risk where third-party models are incorporated without strong behavioral guarantees.<n>We show that poisoned models maintain state-of-the-art performance on benign tasks, incentivizing their adoption.
  arXiv  Detail & Related papers  (2026-03-02T22:01:08Z)
• Evaluating and Understanding Scheming Propensity in LLM Agents [4.5440569375419715]
  We decompose scheming incentives into agent factors and environmental factors.<n>We find minimal instances of scheming despite high environmental incentives, and show this is unlikely due to evaluation awareness.
  arXiv  Detail & Related papers  (2026-03-02T08:38:40Z)
• DLLM Agent: See Farther, Run Faster [94.74432470237817]
  Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
  arXiv  Detail & Related papers  (2026-02-07T09:01:18Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Are Your Agents Upward Deceivers? [73.1073084327614]
  Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users.<n>This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment.<n>We observe and define agentic upward deception, a phenomenon in which an agent facing environmental constraints conceals its failure and performs actions that were not requested without reporting.
  arXiv  Detail & Related papers  (2025-12-04T14:47:05Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents [30.378925170216835]
  Self-replication risk of Large Language Model (LLM) agents driven by objective misalignment has drawn growing attention.<n>We present a comprehensive evaluation framework for quantifying self-replication risks.
  arXiv  Detail & Related papers  (2025-09-29T17:49:50Z)
• SAND: Boosting LLM Agents with Self-Taught Action Deliberation [53.732649189709285]
  Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts.<n>We propose Self-taught ActioN Deliberation (SAND) framework, enabling LLM agents to explicitly deliberate over candidate actions before committing to one.<n>SAND achieves an average 20% improvement over initial supervised finetuning and also outperforms state-of-the-art agent tuning approaches.
  arXiv  Detail & Related papers  (2025-07-10T05:38:15Z)
• MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction [1.3102025155414727]
  Accident severity prediction plays a critical role in transportation safety systems.<n>Existing methods often rely on monolithic models or black box prompting.<n>We propose a multiagent rule based LLM engine that decomposes the severity prediction task across a team of specialized reasoning agents.
  arXiv  Detail & Related papers  (2025-07-07T11:27:49Z)
• Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm [57.00627691433355]
  We frame agent behavior steering as a model editing task, which we term Behavior Editing.<n>We introduce BehaviorBench, a benchmark grounded in psychological moral theories.<n>We demonstrate that Behavior Editing can be used to promote ethical and benevolent behavior or, conversely, to induce harmful or malicious behavior.
  arXiv  Detail & Related papers  (2025-06-25T16:51:51Z)
• MAEBE: Multi-Agent Emergent Behavior Framework [0.0]
  This paper introduces the Multi-Agent Emergent Behavior Evaluation framework to assess such risks.<n>Our findings underscore the necessity of evaluating AI systems in their interactive, multi-agent contexts.
  arXiv  Detail & Related papers  (2025-06-03T16:33:47Z)
• AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models [23.916663925674737]
  Previous work has shown that current LLM-based agents execute numerous malicious tasks even without being attacked.<n>We propose AgentAlign, a novel framework that leverages abstract behavior chains as a medium for safety alignment data synthesis.<n>Our framework enables the generation of highly authentic and executable instructions while capturing complex multi-step dynamics.
  arXiv  Detail & Related papers  (2025-05-29T03:02:18Z)
• Interpretable Risk Mitigation in LLM Agent Systems [0.0]
  We explore agent behaviour in a toy, game-theoretic environment based on a variation of the Iterated Prisoner's Dilemma.<n>We introduce a strategy-modification method-independent of both the game and the prompt-by steering the residual stream with interpretable features extracted from a sparse autoencoder latent space.
  arXiv  Detail & Related papers  (2025-05-15T19:22:11Z)
• AgentRefine: Enhancing Agent Generalization through Refinement Tuning [28.24897427451803]
  Large Language Model (LLM) based agents have proved their ability to perform complex tasks like humans.<n>There is still a large gap between open-sourced LLMs and commercial models like the GPT series.<n>In this paper, we focus on improving the agent generalization capabilities of LLMs via instruction tuning.
  arXiv  Detail & Related papers  (2025-01-03T08:55:19Z)
• Rejecting Hallucinated State Targets during Planning [84.179112256683]
  In planning processes, generative or predictive models are often used to propose "targets" representing sets of expected or desirable states.<n>Unfortunately, learned models inevitably hallucinate infeasible targets that can cause delusional behaviors and safety concerns.<n>We devise a strategy to identify and reject infeasible targets by learning a target feasibility evaluator.
  arXiv  Detail & Related papers  (2024-10-09T17:35:25Z)
• Preemptive Detection and Correction of Misaligned Actions in LLM Agents [70.54226917774933]
  InferAct is a novel approach to detect misaligned actions before execution.<n>It alerts users for timely correction, preventing adverse outcomes.<n>InferAct achieves up to 20% improvements on Marco-F1 against baselines in misaligned action detection.
  arXiv  Detail & Related papers  (2024-07-16T15:24:44Z)
• ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation [48.54271457765236]
  Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values. Current evaluation benchmarks predominantly employ expert-designed contextual scenarios to assess how well LLMs align with human values. We propose ALI-Agent, an evaluation framework that leverages the autonomous abilities of LLM-powered agents to conduct in-depth and adaptive alignment assessments.
  arXiv  Detail & Related papers  (2024-05-23T02:57:42Z)
• How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation [46.42384207122049]
  We design SimulateBench to evaluate the believability of large language models (LLMs) when simulating human behaviors. Based on SimulateBench, we evaluate the performances of 10 widely used LLMs when simulating characters.
  arXiv  Detail & Related papers  (2023-12-28T16:51:11Z)
• Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories [88.08381083207449]
  We show the prevalence of emphgeneralization failure on controllable states from stranger agents. We propose a novel method called Self-Trajectory Augmentation (STA), which will reset the environment to the agent's old states according to the Q function during training.
  arXiv  Detail & Related papers  (2023-04-26T10:12:12Z)
• Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty [54.88405167739227]
  We present HAICU, a method for heterogeneous-agent trajectory forecasting that explicitly incorporates agents' class probabilities. We additionally present PUP, a new challenging real-world autonomous driving dataset. We demonstrate that incorporating class probabilities in trajectory forecasting significantly improves performance in the face of uncertainty.
  arXiv  Detail & Related papers  (2021-04-26T10:28:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.