7 papers
LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning
Xudong Chen, Yixin Liu, Hua Wei +1
Large language models (LLMs) have become a strong foundation for multi-agent systems, but their effectiveness depends heavily on orchestration design. Across different tasks, role…
Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
Jiazheng Li, Chi-Hao Wu, Yunze Liu +3
Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For current multimodal LLMs: even…
Generalizing GNNs with Tokenized Mixture of Experts
Xiaoguang Guo, Zehong Wang, Jiazheng Li +5
Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations. We show that stati…
Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection
Junjun Pan, Yixin Liu, Rui Miao +5
Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical…
Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight
Haolin Yang, Hakaze Cho, Kaize Ding +1
Large Language Models (LLMs) can perform new tasks from in-context demonstrations, a phenomenon known as in-context learning (ICL). Recent work suggests that these demonstrations a…
Tackling Fake Forgetting through Uncertainty Quantification
Yingdan Shi, Sijia Liu, Kaize Ding +1
Machine unlearning seeks to remove the influence of specified data from a trained model. While the unlearning accuracy provides a widely used metric for assessing unlearning perfor…