4 papers
Cordon: Semantic Transactions for Tool-Using LLM Agents
Zheng Chen, Hanqing Liu, Duling Xu +4
Tool-using LLM agents are shifting the unit of computation from explicit human-issued commands to model-driven tasks with stateful consequences. Yet today's agent runtimes still ex…
SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
Duling Xu, Zheng Chen, Zaifeng Pan +4
Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the a…
AuroraRL: Fast, Fault-Tolerant, and Cost-Efficient Reinforcement Learning over Decentralized Network
Chaoyi Ruan, Geng Luo, Xinyi Wan +12
LLM reinforcement learning (RL) requires frequent synchronization of large model parameters between the trainer and distributed rollout actors. High-throughput RL post-training the…
Performant Synchronization in Geo-Distributed Databases
Duling Xu, Tong Li, Zegang Sun +5
The deployment of databases across geographically distributed regions has become increasingly critical for ensuring data reliability and scalability. Recent studies indicate that d…