Metraipolis › archive › dc_85555b707181

Substrate-Aware AI Agents: Execution Context as a First-Class Input — arXiv:2609.05232

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05232
License (as archived)
CC0-1.0
Archived
2026-10-16T22:21:17.127Z
SHA-256 of the archived text
973eb748797e7249380fbd9cbb9a905eb66b903d787697c8f339d9eca73a7feb
Stable URL of this page
https://metraipolis.com/documento/dc_85555b707181

How to cite

Substrate-Aware AI Agents: Execution Context as a First-Class Input — arXiv:2609.05232 — arXiv (en), https://arxiv.org/abs/2609.05232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85555b707181 (Metraipolis archive dc_85555b707181, sha256 973eb748797e7249380fbd9cbb9a905eb66b903d787697c8f339d9eca73a7feb)
BibTeX
@misc{dc85555b707181,
  title = {Substrate-Aware AI Agents: Execution Context as a First-Class Input — arXiv:2609.05232},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05232},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85555b707181; sha256 973eb748797e7249380fbd9cbb9a905eb66b903d787697c8f339d9eca73a7feb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine what counts as a suitable plan. We call the absence of this execution context from an agent's planning state substrate blindness. We test this general proposition through numerical code generation, where selected implementation choices and operational consequences are directly observable. Three frontier model configurations--Anthropic Claude Opus 5, OpenAI GPT-5.6-Sol, and Google Gemini 3.7 Flash--generate code for a high-dimensional pairwise Euclidean-distance task either from the task alone or with a 128 MB RAM and 10.0 s wall-time contract. Contract disclosure reduced measured peak process memory in 13 of 14 executable index-aligned task-only versus contract-disclosed comparisons and reduced mean wall time in all three cohorts, making execution up to 3.1x faster. Across the audited corpus, disclosure produced structural code changes including bounded blocking, float32 retention, upper-triangle traversal, and in-place or memory-mapped buffers. At a tighter 96 MB contract, independently sampled contract-disclosed cohorts achieved correct-and-within-budget outcomes of 4/5 for Claude Opus 5, 5/5 for GPT-5.6-Sol, and 3/5 for Gemini 3.7 Flash, compared with task-only outcomes of 0/5, 1/5, and 0/5; cohort mean MaxRSS and wall time were 49-74% and 35-64% lower than their task-only references. These results establish a controlled proof of concept for substrate-aware agent planning: a minimal execution contract induces proactive structural adaptation in generated programs, shifting computation away from unconstrained allocations and substantially improving observed resource-time profiles before execution.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05232 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T22:18:11.445Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).