Substrate-Aware AI Agents: Execution Context as a First-Class Input
- 类型：arxiv
- 标识：2609.05232
- 链接：http://arxiv.org/abs/2609.05232v1
- 主分类：agent
- 形态：position
- TLDR：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 Eu
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-07-agent-rag-longcontext-candidates.json