arXiv:2605. 03353v3 Announce Type: replace-cross Abstract: LLM agents increasingly rely on reusable skills (e.
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:2603. 20075v2 Announce Type: replace-cross Abstract: Compilers are critical to modern computing, yet fixing compiler bugs is difficult.
BuildBench introduces a realistic benchmark for evaluating large language model agents on the task of compiling open‑source software (OSS). It includes diverse OSS projects that lack clear build instructions, have undocumented dependencies, and may require source patching or script modification. The authors also present OSS‑BUILD‑AGENT, a baseline LLM‑based agent that retrieves build instructions effectively and achieves state‑of‑the‑art performance on the benchmark.
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...
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.
arXiv:2607. 03451v1 Announce Type: cross Abstract: While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines.
arXiv:2607. 04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded.