Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework

• URL: http://arxiv.org/abs/2604.22119v1
• Date: Thu, 23 Apr 2026 23:44:01 GMT
• Title: Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
• Abstract summary: Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
• Score: 63.74295981594549
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs). These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking (exploiting misspecified objectives). Systematically understanding and benchmarking these risks remains an open challenge. To address this gap, we introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation. We construct an extensible risk taxonomy of 7 categories, which is decomposed into 20 subcategories. ESRRSim generates evaluation scenarios designed to elicit faithful reasoning, paired with dual rubrics assessing both model responses and reasoning traces, in a judge-agnostic and scalable architecture. Evaluation across 11 reasoning LLMs reveals substantial variation in risk profiles (detection rates ranging 14.45%-72.72%), with dramatic generational improvements suggesting models may increasingly recognize and adapt to evaluation contexts.

Related papers

• The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents [37.75212140218036]
  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.
  arXiv  Detail & Related papers  (2026-01-24T07:09:50Z)
• Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse [50.87630846876635]
  We develop nine detailed cyber risk models.<n>Each model decomposes attacks into steps using the MITRE ATT&CK framework.<n>Individual estimates are aggregated through Monte Carlo simulation.
  arXiv  Detail & Related papers  (2025-12-09T17:54:17Z)
• A Methodology for Quantitative AI Risk Modeling [32.594929429306774]
  This paper advances the risk modeling component of AI risk management by introducing a methodology that integrates scenario building with quantitative risk estimation.<n>Our methodology is designed to be applicable to key systemic AI risks, including cyber offense, biological weapon development, harmful manipulation, and loss-of-control.
  arXiv  Detail & Related papers  (2025-12-09T17:34:59Z)
• SafeRBench: A Comprehensive Benchmark for Safety Assessment in Large Reasoning Models [60.8821834954637]
  We present SafeRBench, the first benchmark that assesses LRM safety end-to-end.<n>We pioneer the incorporation of risk categories and levels into input design.<n>We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units.
  arXiv  Detail & Related papers  (2025-11-19T06:46:33Z)
• RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration [81.38705556267917]
  Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations.<n>We introduce a theoretical framework that reconstructs the underlying risk concept space.<n>We propose RADAR, a multi-agent collaborative evaluation framework.
  arXiv  Detail & Related papers  (2025-09-28T09:35:32Z)
• CORTEX: Composite Overlay for Risk Tiering and Exposure in Operational AI Systems [0.812761334568906]
  This paper introduces CORTEX, a multi-layered risk scoring framework to assess and score AI system vulnerabilities.<n>It was developed on empirical analysis of over 1,200 incidents documented in the AI Incident Database (AIID)<n>The resulting composite score can be operationalized across AI risk registers, model audits, conformity checks, and dynamic governance dashboards.
  arXiv  Detail & Related papers  (2025-08-24T07:30:25Z)
• Exploring the Secondary Risks of Large Language Models [26.00748215572094]
  We introduce secondary risks marked by harmful or misleading behaviors during benign prompts.<n>Unlike adversarial attacks, these risks stem from imperfect generalization and often evade standard safety mechanisms.<n>We propose SecLens, a black-box, multi-objective search framework that efficiently elicits secondary risk behaviors.
  arXiv  Detail & Related papers  (2025-06-14T07:31:52Z)
• Adapting Probabilistic Risk Assessment for AI [0.0]
  General-purpose artificial intelligence (AI) systems present an urgent risk management challenge.<n>Current methods often rely on selective testing and undocumented assumptions about risk priorities.<n>This paper introduces the probabilistic risk assessment (PRA) for AI framework.
  arXiv  Detail & Related papers  (2025-04-25T17:59:14Z)
• Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework [77.45983464131977]
  We focus on how likely it is that a RAG model's prediction is incorrect, resulting in uncontrollable risks in real-world applications.<n>Our research identifies two critical latent factors affecting RAG's confidence in its predictions.<n>We develop a counterfactual prompting framework that induces the models to alter these factors and analyzes the effect on their answers.
  arXiv  Detail & Related papers  (2024-09-24T14:52:14Z)
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents [53.717918131568936]
  Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction.<n>Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results.<n>However, the deployment of these agents in physical environments presents significant safety challenges.<n>This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)

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.