Conflicts Make Large Reasoning Models Vulnerable to Attacks
Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries when confronted with two categories of conflicts: internal conflicts that pit alignment values against each other and dilemmas, which impose mutually contradictory choices, including sacrificial, duress, agent-centered, and social forms. Using over 1,300 promp
Record details
Published: 10 April 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Agents & autonomy · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis
arXiv · 9 April 2026
ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
arXiv · 23 June 2026
ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs
arXiv · 15 July 2026
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
HuggingFace Daily Papers · 26 July 2026
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
arXiv · 27 July 2026
Effect of a robotic insole-type active assist device on horizontal ground reaction force and center-of-pressure stability during stepping in patients with medial knee osteoarthritis
Frontiers in Robotics and AI · 12 August 2026
How to cite this record
ethics.ai (10 April 2026), “Conflicts Make Large Reasoning Models Vulnerable to Attacks,” evidence record 6069, https://ethics.ai/record/6069 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.