When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leaving privilege-sensitive choices underexplored. To address this gap, we study over-privileged tool selection, in which an agent selects or escalates to a higher-privilege tool despite a sufficient lower-privilege alternative. We introduce ToolPrivBench to evaluate whether agents ch
Record details
Published: 18 June 2026
Source: arXiv
Category: Research
Topics: 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.
Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models
arXiv · 16 June 2026
From Parasocial Scripts to Dyadic Persistence in Autonomous AI-Agent Communities
arXiv · 15 June 2026
IPO Finance Agent: Benchmark of LLM Financial Analysts Beyond Finance Agent v2, with Automated Rubric Generation, on the SpaceX (SPCX) IPO
arXiv · 22 June 2026
ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
arXiv · 23 June 2026
Pingquanqi (Equalizer): A Cross-Domain Sociotechnical Framework for Human-Agent Interaction Governance
arXiv · 25 June 2026
The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models
arXiv · 9 June 2026
How to cite this record
ethics.ai (18 June 2026), “When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents,” evidence record 811, https://ethics.ai/record/811 (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.