Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

Kaiyue Yang, Yuyan Bu, Jingwei Yi, Yuchi Wang +4 more

Published

Jun 18, 2026

Citations

0

Trust level

Moderate

Usefulness score

50/100 (Medium)

Extraction confidence

60% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Jun 18, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

General Pairwise Preference Tool Use

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
50/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

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 choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures. Across eight domains and five recurring risk patterns, we find that over-privileged tool selection is common among mainstream LLM agents and is further amplified by transient failures. We further find that general safety alignment does not reliably transfer to least-privilege tool choice, while prompt-level controls provide only limited mitigation under transient failures. We therefore introduce a privilege-aware post-training defense that teaches agents to prefer sufficient lower-privilege tools and escalate only when necessary. Our mitigation experiments show that this defense substantially reduces unnecessary high-privilege tool use while preserving general capabilities.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Pairwise Preference

Directly usable for protocol triage.

"As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant."

Quality Controls

missing

Not reported

No explicit QC controls found.

"As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant."

Benchmarks / Datasets

strong

Toolprivbench

Useful for quick benchmark comparison.

"We introduce ToolPrivBench to evaluate whether agents choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant."

Benchmarks and datasets

Toolprivbench

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Pairwise Preference
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
Tool Use
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • 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.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Tool-use evaluation) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • 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.
  • We introduce ToolPrivBench to evaluate whether agents choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures.

Why it matters for eval

  • As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant.
  • We introduce ToolPrivBench to evaluate whether agents choose higher-privilege tools despite sufficient lower-privilege alternatives, measuring both initial selection and escalation after transient tool failures.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: Toolprivbench

  • Metric reporting is present

    No metric terms extracted.