Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
Fewshot Corp * Independent Researcher
3
0
4
6
Future LLM agents can be prevented from reward hacking by using today's models to automatically harden their evaluation environments.
Popular terminal-agent benchmarks are riddled with flaws, with over 15% of tasks being easily reward-hackable, undermining their ability to accurately assess LLM capabilities.
Frontier LLMs are surprisingly vulnerable to a wide range of task-specific exploits, from simple output spoofing to rootkit-style binary hijacking, even in seemingly well-defined environments.