8 papers
MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems
Haobo Zhang, Xutao Mao, Guangyuan Dong +5
Memory-backed agents need provenance that can survive leaked or migrated snapshots, where logs, visible outputs, and trusted metadata may be absent. We propose MemMark, a state-evo…
Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents
Yuxin Zhang, Mengxue Hu, Zheng Lin +8
Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundame…
Causal Path Alignment: Anchoring the Optimization Trajectory for Controllable In-Parameter Knowledge Editing
Xiyu Liu, Zhengxiao Liu, Naibin Gu +2
Knowledge editing is pivotal for efficiently updating the parametric memory of Large Language Models (LLMs), enabling them to function as evolving agents in dynamic environments. H…
Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
Zheng Lin, Zhenxing Niu, Haoxuan Ji +2
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a mo…
Propagation of Chaos in Contextual Flow Maps
Shi Chen, Zhengjiang Lin, Kaizhao Liu +1
We develop a quantitative statistical theory of transformers in the large-context regime by adopting the abstraction of contextual flow maps (CFMs): dynamical systems that evolve a…
LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation
Lingyu Mu, Hao Deng, Haibo Xing +7
Recent progress in large language model (LLM) based generative recommendation (GR) shows that leveraging LLM world knowledge can substantially improve performance. However, existin…