6 papers
A Mechanistic Study of Automated Failure Attribution in LLM-based Agentic Systems
Wendy Zheng, Liang Wu, Yinhan He +3
Agentic systems have demonstrated strong capabilities on complex tasks by enabling multiple interacting large language model (LLM)-based agents to collaborate and execute subtasks…
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Guanghui Min, Liang Wu, Mingjia Shi +4
Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing pr…
Self-Evolving Code-with-Image Reasoning
Tianze Yang, Liang Wu, Ruitong Sun +6
Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The central challenge is one of p…
Towards Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
Guanghui Min, Liang Wu, Mayank Darbari +2
Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study, we show that…
WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware
Jiamu Zhang, Liang Wu, Mayank Darbari +1
Modern local and agentic workloads often need large-model capacity at low concurrency, but run on GPUs that cannot keep a frontier-scale model resident. Mixture-of-Experts (MoE) mo…
Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G
Liang Wu, Kelly Wan, Mayank Darbari +1
The proliferation of emerging applications, such as autonomous driving and immersive experiences, demands cellular networks that are not only faster, but fundamentally more resilie…