← Back to the feed
Space & aviationResearch findings

EpiSEM-Bench: Framework for Safety Evaluation and Evidence Recovery under Missing Evidence

Original published 2026.10.23 02:57 KSTAdded to Blackdeck 2026.10.26 14:53 KST

What has changed?

Introduces an executable benchmark with 300 matched unsafe/safe task pairs across six domains.

Key points

  1. Tool-using LLM agents rely on environmental facts to determine action permissibility.
  2. Omission of safety-relevant facts can lead to prohibited actions despite benign user requests.
  3. EpiSEM-Bench evaluates unsafe execution and evidence recovery under missing evidence.

Connect it to your work

Measures unsafe execution under critical evidence omission and evaluates recovery behavior in response to missing facts.

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivEpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence