Hao Zheng

The paper introduces RLSpoofer, a lightweight, black-box reinforcement learning attack that demonstrates the fragile resilience of current LLM watermarking schemes by achieving a high spoofing success rate with minimal training data.

The paper introduces Evidence-Carrying Agents (ECA) to prevent multimodal agents from executing privileged actions based on unsupported or hallucinated perceptual claims, achieving near-zero unsafe execution rates.

The paper demonstrates that extrapolative weight averaging can effectively navigate and extend the correctness-efficiency frontier in code RL, leading to improved performance on complex programming tasks.

The paper introduces Dr-CiK, a new benchmark designed to evaluate agents' ability to proactively discover, filter, and utilize relevant external context for time series forecasting, demonstrating that current agents struggle significantly with this task.