Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools, execute commands, and interact with task-specific services. These workloads create sandboxes in large bursts, span heterogeneous functionali...
Jia-Liang Huang, Hong-Xuan Tang, Jing-Chang Chen et al.· 3 citations
Agentic Reinforcement Learning (RL) trains LLM agents through multi-turn interactions with external tool environments. Its multi-turn nature exposes two system-level bottlenecks unaddressed by existing agentic RL frameworks. First, end-to-end training throughput is constrained by the slowest trajectories to complete, y...
Ming-Jun Zhang, Yu-Cheng Li, Meng-Hao Zhang et al.· 0 citations
PIVOT, Proxy Indexing Via One full-prefix Traversal, a training-free, drop-in replacement for the DSA indexer that shares one prefix scan across a group of nearby queries, matches the accuracy of the dense DSA indexer while accelerating it by up to 4x and reducing end-to-end latency by up to 1.6x at long context.
Hong Liu, Yuan Cheng, Lin Niu et al.· arXiv.org· 3 citations
DualDecoder is presented, a lightweight serving system for long-context LLM inference that enables efficient sparse KV cache retrieval from host memory that leverages a novel dual-token decoding pipeline that accurately identifies critical KV entries with negligible computational overhead.
