14 papers
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
Xinmu Ge, Zizhuo Zhang, Yu Huang +9
On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. It is commonly believed to enable the student model to distill knowledg…
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
Zhangheng LI, Jianing Zhu, Junyuan Hong +4
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sen…
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
Jianing Zhu, Yeonju Ro, John Robertson +5
Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic syst…
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
Jingwei Sun, Jianing Zhu, Yuanyi Li +3
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-w…
When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
John T. Robertson, Jianing Zhu, Haris Vikalo +1
Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts. Prior work often reads this variability as ev…
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
Jingwei Sun, Jianing Zhu, Jiangchao Yao +2
To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. M…