8 papers
DuplexLedger: Benchmarking Transactional Memory in Full-Duplex Speech Agents
Yuxuan Li, Xiangchen Guan, Kunrong Li +7
Full-duplex speech agents must update persistent memory while listening and speaking, yet it remains unclear which events should be stored, revised, or excluded. Existing benchmark…
MemoWM: How World Models Change What Agents Need to Remember
Bingfan Zeng, Zhisheng Chen, Chenbo Sang +6
Long-term agents face growing storage demands as they accumulate experience. World models capture reusable regularities that can reduce the information stored for each experience.…
Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL
Qizhen Lan, Xi Xiao, Xiangchen Guan +4
On-policy self-distillation (OPSD) gives language agents dense token-level supervision from a privileged self-teacher on the policy's own trajectories. Existing methods allocate th…
The Uncontrolled Variable: Vision-Language Refusal Is Conditioned on the Image-Attachment Interface, and Not Robust to Irrelevant Image Properties
Haoyu Zhang, Yi Feng, Shibo Zheng +8
We show that aligned vision-language models also condition refusal on a property of a request's form: whether an image is attached, holding everything the request asks fixed. Attac…
Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks
Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2
We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrela…
Blind, Not Weak: A Best-of-Suite Safety-Utility Frontier for Recover-and-Reguard Defenses Against Encoded VLM Jailbreaks
Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +9
Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encod…
MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
Zhisheng Chen, Bingfan Zeng, Bangde Cao +8
Long-horizon agents performing multi-step Web tasks must reuse earlier page observations and interactions to support subsequent actions. However, preserving relevant history does n…
Depth, Not Breadth: Best-of-N Jailbreaking Beyond Surface Noise
Haoyu Zhang, Shibo Zheng, Hanwen Liu +9
Best-of-N jailbreaking spends a query budget on surface variation, scrambling and recasing a request until one draw lands. We ask what the same search buys when it wraps a structur…