collaborators

5 papers

cs.LG2026

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

Sarvesh Patil, Mitsuhiko Nakamoto, Manan Agarwal +14

Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-pol…

cs.CR2026

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

Ziqian Zhong, Ivgeni Segal, Ivan Bercovich +3

Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1,968 tasks across five termina…

cs.CR2026

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

Ivan Bercovich, Ivgeni Segal, Kexun Zhang +3

We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set inclu…

cs.AI2026

Hodoscope: Unsupervised Monitoring for AI Misbehaviors

Ziqian Zhong, Shashwat Saxena, Aditi Raghunathan

Existing approaches to monitoring AI agents rely on supervised evaluation: human-written rules or LLM-based judges that check for known failure modes. However, novel misbehaviors m…

cs.CR2025

Jailbreaking in the Haystack

Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena +3

Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks like computer-use agents. Yet, the safety…