EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence
Factual evidence
What the source reports
Researchers introduced EpiSEM-Bench, a benchmark evaluating tool-using LLM agent safety and execution when evidence is missing.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.LG — Machine Learning · RESEARCH
- Published by source
- 23 October 2026
- Collected by OneBench
- 24 Oct 2026, 03:02 UK
Stored source excerpt
arXiv:2610.31650v1 Announce Type: cross Abstract: Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.
OneBench interpretation
Institutional assessment
So what
Tool-using AI agents may execute unsafe financial transactions if API responses omit crucial safety facts, exposing gaps in standard guardrails.
Do what
Review agentic workflow failure modes with the model risk team to ensure tools handle incomplete data safely.