Reinforcement learning (RL) has emerged as a critical phase in the post-training pipeline of large language models (LLMs). As the frontier of LLM capabilities shifts from static reasoning to agentic tasks--characterized by external tool invocation, multi-turn interactions, and long-horizon decision-making--existing mai...
LoongSage Team Bowei Song, Cai-Wei Zhao, Chu-Wen Liu et al.· 0 citations
This paper discusses how CloudWeaver scopes the context of individual agent sessions with local views of cloud resources and coordinates concurrent management operations on shared cloud resources, and offers strong safety guarantees and attributable feedback in the presence of conflicting intents, while preserving conc...
Minghao Li, Ziqian Liu, Ziyu Mao et al.· arXiv.org· 0 citations
The model is a stateful computational middlebox inside a human-centered feedback loop, with network transport, model serving, and user playback jointly shaping how the interaction evolves, and is called for an AI-native real-time communication stack that resolve the joint control problem spanning communication, computa...
