arXiv:2606.18746v1 Announce Type: new Abstract: This paper develops a formal account of what generalist agents must store in memory in order to act near-optimally across multiple environments and goals. It shows that when two domains share an observational bottleneck but require incompatible optimal actions, any uniformly near-optimal policy must induce distinct memory distributions at that bottleneck. The result yields a separation theorem: sufficiently successful agents cannot rely only on cur
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Artificial Intelligence
[Submitted on 17 Jun 2026]
What Must Generalist Agents Remember?
Khurram Yamin, Namrata Deka, Maitreyi Swaroop, Albert Ting, Jeff Schneider, Bryan Wilder
This paper develops a formal account of what generalist agents must store in memory in order to act near-optimally across multiple environments and goals. It shows that when two domains share an observational bottleneck but require incompatible optimal actions, any uniformly near-optimal policy must induce distinct memory distributions at that bottleneck. The result yields a separation theorem: sufficiently successful agents cannot rely only on current state observations, but must preserve domain-relevant information in memory. The paper further shows that if an agent's memory contains enough information to estimate values for related goals, then that memory can be used to approximately reconstruct the agent's local transition dynamics. Together, these results characterize memory as the substrate that supports domain disambiguation, transition-model reconstruction, and planning for generalist agents.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.18746 [cs.AI]
(or arXiv:2606.18746v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.18746
Focus to learn more
Submission history
From: Khurram Yamin [view email]
[v1] Wed, 17 Jun 2026 06:46:51 UTC (851 KB)
Access Paper:
HTML (experimental)
view license
Current browse context:
cs.AI
< prev | next >
new | recent | 2026-06
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?)