Metraipolis › archive › dc_c19ce25d62a3

Planarian: Managing Agent State with Statepoints — arXiv:2609.35366

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35366
License (as archived): CC0-1.0
Archived: 2026-10-07T21:03:31.140Z
SHA-256 of the archived text: c738631e2cf3c54393290ce9e5c70e0ee6f711b4ef4430078216592dcfa8df48
Stable URL of this page: https://metraipolis.com/documento/dc_c19ce25d62a3

How to cite

Planarian: Managing Agent State with Statepoints — arXiv:2609.35366 — arXiv (en), https://arxiv.org/abs/2609.35366 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c19ce25d62a3 (Metraipolis archive dc_c19ce25d62a3, sha256 c738631e2cf3c54393290ce9e5c70e0ee6f711b4ef4430078216592dcfa8df48)

BibTeX

@misc{dcc19ce25d62a3,
  title = {Planarian: Managing Agent State with Statepoints — arXiv:2609.35366},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35366},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c19ce25d62a3; sha256 c738631e2cf3c54393290ce9e5c70e0ee6f711b4ef4430078216592dcfa8df48},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35366. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents solve complex tasks by iteratively changing files, invoking local tools, and interacting with remote services, which modifies state across their local environment and remote services. Today, agents and users must manage these changes explicitly, whether reverting exploratory actions or recovering from erroneous ones. Doing so safely requires coordinated actions, yet current agent harnesses lack unified abstractions and mechanisms for managing local and remote state consistently and efficiently. We describe Planarian, an agent runtime with state management that enables agents and users to recover from erroneous actions and explore alternative executions over consistent local and remote environment state. Planarian introduces the abstraction of agent statepoints, which are consistent, restorable point-in-time versions of the environment state. Planarian exposes three state-management primitives to agents and users: (i) snapshot creates a new statepoint spanning local and remote state without requiring external services to support checkpoints: it relies on efficient incremental process and file system snapshotting to capture local sandboxed state, and transparently records compensating actions to undo remote state changes; (ii) rollback restores the environment to a previous statepoint by reverting to a prior local checkpoint and replaying compensating actions for remote state changes; and (iii) fork creates multiple isolated branches from a statepoint, enabling the agent to explore alternatives in parallel. We show that Planarian enables agents to undo mistakes and explore alternatives in parallel, improving task quality by up to 15x, and allows users to recover from erroneous actions with only 3% overhead.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Operating Systems (cs.OS) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.35366 — 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 2026-10-07T20:29:03.334Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).