5 citations · 8 across the 12 of their papers we have counts for
7 papers · 1 filter
EAT: Expert Account Tracker for Efficient MoE Inference
Yuexian Li, Yifei Yang, Zouying Cao +1
Mixture-of-Experts (MoE) models have emerged as a revolutionary method to scale Transformer models. However, traditional MoE architecture still suffers from inefficiency since a la…
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
Shan He, Runze Wang, Zhuoyun Du +4
Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat…
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
Zouying Cao, Jiaji Deng, Li Yu +4
Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predom…
ParaCook: On Time-Efficient Planning for Multi-Agent Systems
Shiqi Zhang, Xinbei Ma, Yunqing Xu +7
Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting…
PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
Zouying Cao, Runze Wang, Yifei Yang +4
Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to…
Plan-over-Graph: Towards Parallelable LLM Agent Schedule
Shiqi Zhang, Xinbei Ma, Zouying Cao +2
Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper in…
SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering
Zouying Cao, Yifei Yang, Hai Zhao
Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to rej…