Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2510.20270
Cited By
ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
23 October 2025
Ziqian Zhong
Aditi Raghunathan
Nicholas Carlini
Re-assign community
ArXiv (abs)
PDF
HTML
HuggingFace (5 upvotes)
Github (1★)
Papers citing
"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases"
2 / 2 papers shown
Title
Are Your Agents Upward Deceivers?
Dadi Guo
Qingyu Liu
Dongrui Liu
Qihan Ren
Shuai Shao
...
Z. Chen
Jialing Tao
Yaodong Yang
Jing Shao
Xia Hu
LLMAG
112
0
0
04 Dec 2025
EvilGenie: A Reward Hacking Benchmark
Jonathan Gabor
Jayson Lynch
Jonathan Rosenfeld
ELM
99
0
0
26 Nov 2025
1
