arXiv:2512. 25065v2 Announce Type: replace-cross Abstract: Systems resource management tasks rely primarily on hand-designed heuristics.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2606. 08976v1 Announce Type: new Abstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation.
arXiv:2601. 09923v3 Announce Type: replace Abstract: AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior.
arXiv:2606. 06256v1 Announce Type: new Abstract: As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure.
Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when models turn this guidance into code for existing too...
Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state.
SkillEffect is a checked‑lowering runtime that ensures agent tool calls stay within memory limits by verifying each proposed program against an immutable input before execution. It uses audited relation plugins to provide source recognition, bounded intermediate representation construction, and postconditions, while a shared runtime handles selection, bounded VM execution, and atomic capacity leasing. Experiments across six operator families show that bounded access significantly reduces peak memory usage and improves completion rates under fixed memory caps.