#artificial intelligence
Sep 2026
SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
This work introduces SINGED (Source Integrity and the Nonidentifiability Gap in Execution Decisions for LLM Agents), a controlled benchmark covering five primary and two held-out task families and exposes a rank-, evidence-, and choice-sensitive outcome-to-execution gap.
XiaoYu Xu, Zi Liang, Min-Xin Du et al.
· arXiv.org · 0 citations