Metraipolis › archive › dc_39c41eebe8d1
StateFork: Branchable Infrastructure for Agent Exploration — arXiv:2609.38648
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38648
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T15:20:08.181Z
- SHA-256 of the archived text
3e42973d6bf36089f28545bb4a01643ccd456e7e5e7bbb32800b89bd570c0517- Stable URL of this page
https://metraipolis.com/documento/dc_39c41eebe8d1
How to cite
StateFork: Branchable Infrastructure for Agent Exploration — arXiv:2609.38648 — arXiv (en), https://arxiv.org/abs/2609.38648 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39c41eebe8d1 (Metraipolis archive dc_39c41eebe8d1, sha256 3e42973d6bf36089f28545bb4a01643ccd456e7e5e7bbb32800b89bd570c0517)
BibTeX
@misc{dc39c41eebe8d1,
title = {StateFork: Branchable Infrastructure for Agent Exploration — arXiv:2609.38648},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38648},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39c41eebe8d1; sha256 3e42973d6bf36089f28545bb4a01643ccd456e7e5e7bbb32800b89bd570c0517},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38648. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents improve task success by exploring multiple trajectories, but for computer-use agents each trajectory modifies external environment state. Branching from an intermediate point is correct only when restoration is observation-equivalent - future actions produce the same observations - and practical only when creating, restoring, and discarding branch states is physically efficient. We study this problem for terminal-using agents, where tasks modify files, shell context, running processes, and local services. We introduce StateFork, a logical control plane that separates exploration policies from physical state materialization, exposing sessions, commands, snapshots, restores, and cleanup over multiple execution substrates. We also build Waypoint, a checkpoint/restore substrate for terminal execution sessions that combines filesystem layering, process checkpointing, and a persistent terminal-compatible command session. Together, StateFork and Waypoint improve terminal-agent exploration by combining sample-efficient search with efficient restoration of the right execution state. On Terminal-Bench, branch-based exploration through StateFork and Waypoint improves task completion over pass@20 at the same visited-node budget, and using Waypoint achieves 26% higher task accuracy than other execution substrates while completing exploration up to 70% faster. These results show that observation-equivalent, physically efficient execution sessions are a key systems abstraction for exploratory AI agents. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-10-01 in cs.OS). Categorie arXiv: Operating Systems (cs.OS). Pagina del lavoro: https://arxiv.org/abs/2609.38648 — 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 2026-10-07T14:53:17.068Z dalla pagina https://arxiv.org/catchup/cs.OS/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).