works on

From the 2 of 5 linked papers with an AI index.

collaborators

5 papers

cs.AI2026

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…

cs.AI2026

MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents

Zhisheng Chen, Bingfan Zeng, Bangde Cao +8

Long-horizon agents rely on memory to reuse experiences, yet existing memory systems often assume that evidence can be directly consumed through a fixed representation. This leads…

cs.CR2026

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…

cs.CR2026

Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses

Haoyu Zhang, Shibo Zheng, Xiangchen Guan +4

The paper demonstrates that a self‑check defense (SAGE) for language models can be bypassed by combining a code‑completion encoding attack with a best‑of‑N search, dramatically inc…

cs.CR2026

Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks

Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +7

The paper proposes a guard‑agnostic recovery‑and‑decode module that transcribes encoded or visual text into plain language before applying existing safety classifiers for vision‑la…