Substrate-Aware AI Agents: Execution Context as a First-Class Input

The paper introduces the concept of substrate blindness, where AI agents lack execution context in their planning. By providing a 128 MB RAM and 10 s wall‑time contract to large language models, the authors show that agents generate code that uses less memory, runs faster, and incorporates structural changes such as bounded blocking and in‑place buffers. Across three leading models, contract disclosure improved resource usage and correctness, demonstrating that minimal execution contracts can guide agents to produce more efficient programs.

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.

• llms
• agents