The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents

• URL: http://arxiv.org/abs/2601.17344v1
• Date: Sat, 24 Jan 2026 07:09:50 GMT
• Title: The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents
• Authors: Chen Chen, Kim Young Il, Yuan Yang, Wenhao Su, Yilin Zhang, Xueluan Gong, Qian Wang, Yongsen Zheng, Ziyao Liu, Kwok-Yan Lam,
• Abstract summary: We formalize the Loss-of-Control risk and identify the previously underexamined Intrinsic Value Misalignment (Intrinsic VM)<n>We then introduce IMPRESS, a scenario-driven framework for systematically assessing this risk.<n>We evaluate Intrinsic VM on 21 state-of-the-art LLM agents and find that it is a common and broadly observed safety risk across models.
• Score: 37.75212140218036
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue objectives that deviate from human values and ethical norms, a risk known as value misalignment. Existing evaluations primarily focus on responses to explicit harmful input or robustness against system failure, while value misalignment in realistic, fully benign, and agentic settings remains largely underexplored. To fill this gap, we first formalize the Loss-of-Control risk and identify the previously underexamined Intrinsic Value Misalignment (Intrinsic VM). We then introduce IMPRESS (Intrinsic Value Misalignment Probes in REalistic Scenario Set), a scenario-driven framework for systematically assessing this risk. Following our framework, we construct benchmarks composed of realistic, fully benign, and contextualized scenarios, using a multi-stage LLM generation pipeline with rigorous quality control. We evaluate Intrinsic VM on 21 state-of-the-art LLM agents and find that it is a common and broadly observed safety risk across models. Moreover, the misalignment rates vary by motives, risk types, model scales, and architectures. While decoding strategies and hyperparameters exhibit only marginal influence, contextualization and framing mechanisms significantly shape misalignment behaviors. Finally, we conduct human verification to validate our automated judgments and assess existing mitigation strategies, such as safety prompting and guardrails, which show instability or limited effectiveness. We further demonstrate key use cases of IMPRESS across the AI Ecosystem. Our code and benchmark will be publicly released upon acceptance.

Related papers

• MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Risks in LLMs on Domain Tasks [17.598413159363393]
  Current alignment efforts primarily target explicit risks such as bias, hate speech, and violence.<n>We propose MENTOR: A MEtacognition-driveN self-evoluTion framework for uncOvering and mitigating implicit risks in large language models.<n>We release a supporting dataset of 9,000 risk queries spanning education, finance, and management to enhance domain-specific risk identification.
  arXiv  Detail & Related papers  (2025-11-10T13:51:51Z)
• 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)
• A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents [45.53643260046778]
  Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents.<n>These large-model agents mark a paradigm shift from static inference systems to interactive, memory-augmented entities.
  arXiv  Detail & Related papers  (2025-06-30T13:34:34Z)
• ROSE: Toward Reality-Oriented Safety Evaluation of Large Language Models [60.28667314609623]
  Large Language Models (LLMs) are increasingly deployed as black-box components in real-world applications.<n>We propose Reality-Oriented Safety Evaluation (ROSE), a novel framework that uses multi-objective reinforcement learning to fine-tune an adversarial LLM.
  arXiv  Detail & Related papers  (2025-06-17T10:55:17Z)
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs [83.11815479874447]
  We propose a novel jailbreak attack framework, inspired by cognitive decomposition and biases in human cognition.<n>We employ cognitive decomposition to reduce the complexity of malicious prompts and relevance bias to reorganize prompts.<n>We also introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm.
  arXiv  Detail & Related papers  (2025-05-03T05:28:11Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [1.1666234644810893]
  Small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale.<n>No model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• Conformal Tail Risk Control for Large Language Model Alignment [9.69785515652571]
  General-purpose scoring models have been created to automate the process of quantifying tail events.<n>This phenomenon introduces potential human-machine misalignment between the respective scoring mechanisms.<n>We present a lightweight calibration framework for blackbox models that ensures the alignment of humans and machines with provable guarantees.
  arXiv  Detail & Related papers  (2025-02-27T17:10:54Z)
• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models [75.67623347512368]
  We propose toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T17:14:40Z)
• 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)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)

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.