6 papers
Communication Policy Evolution for Proactive LLM Agents
Xinbei Ma, Jiyang Qiu, Yao Yao +10
LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferen…
Retrospective Progress-Aware Self-Refinement for LLM Agent Training
Xinbei Ma, Congmin Zheng, Jiyang Qiu +10
LLM-based agents trained with reinforcement learning optimize step-wise action prediction but lack metacognitive awareness of task progress, inducing a gap that hinders long-horizo…
Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness
Jiyang Qiu, Xinbei Ma, Yunqing Xu +2
The rapid deployment of large language model (LLM)-based agents in real-world applications has raised serious concerns about their trustworthiness. In this work, we reveal the secu…
MEGen: Generative Backdoor into Large Language Models via Model Editing
Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang +3
Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concern…
Textual-to-Visual Iterative Self-Verification for Slide Generation
Yunqing Xu, Xinbei Ma, Jiyang Qiu +1
Generating presentation slides is a time-consuming task that urgently requires automation. Due to their limited flexibility and lack of automated refinement mechanisms, existing au…
On the Robustness of Editing Large Language Models
Xinbei Ma, Tianjie Ju, Jiyang Qiu +4
Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation…