3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. Verifiers can be attacked into awarding full credit to cheating agents without completing the intended task, causing inaccurate evaluation and misalignment in training. As...
AuraForge is introduced to synthesize and validate executable security tests for training secure coding agents, and it is demonstrated that AuraForge provides more diverse and reliable security supervision to train secure coding agents.
This work adapts HVE to Terminal Bench, a leading benchmark of real-world terminal and coding tasks, and introduces Hack-Verifiable Terminal Bench (HVTB), to measure reward-hacking rates across frontier models and study whether prompts with varying amounts of information on the hack can mitigate this behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
