13 papers
MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
Ming Zhang, Kaisen Yang, Shu Yu +6
Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic comput…
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
Zhida He, Xia Hu, Baichen Le +20
Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4
The paper introduces Deep Interaction, a method that lets users directly edit the chain‑of‑thought output of large language models to fix reasoning errors, resulting in higher corr…
EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
Yu Li, Yuenan Hou, Yingmei Wei +2
Large Language Models (LLMs) remain highly vulnerable to diverse attacks, particularly in black-box settings where the internals of target models are inaccessible. Existing black-b…
TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking
Churui Zeng, Weiwei Qi, Kedong Xiu +5
The rise of LLM agents introduces a new threat by enabling planning, coding, and even end-to-end execution of expert-level attack workflows. However, this threat remains underexplo…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…