Artifacts as Memory Beyond the Agent Boundary

Computer Science > Artificial Intelligence [Submitted on 9 Apr 2026] Artifacts as Memory Beyond the Agent Boundary John D. Martin, Fraser Mince, Esra'a Saleh, Amy Pajak The situated view of cognition holds that intelligent behavior depends not only on internal memory, but on an agent's active use of environmental resources. Here, we begin formalizing this intuition within Reinforcement Learning (RL). We introduce a mathematical framing for how the environment can functionally serve as an agent's memory, and prove that certain observations, which we call artifacts, can reduce the information needed to represent history. We corroborate our theory with experiments showing that when agents observe spatial paths, the amount of memory required to learn a performant policy is reduced. Interestingly, this effect arises unintentionally, and implicitly through the agent's sensory stream. We discuss the implications of our findings, and show they satisfy qualitative properties previously used to ground accounts of external memory. Moving forward, we anticipate further work on this subject could reveal principled ways to exploit the environment as a substitute for explicit internal memory. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.08756 [cs.AI]   (or arXiv:2604.08756v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.08756 Focus to learn more Submission history From: John Martin Jr [view email] [v1] Thu, 9 Apr 2026 20:39:59 UTC (47,637 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)