Metraipolis › archive › dc_3dd72e2e60db
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory — arXiv:2608.16889
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16889
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:07:42.204Z
- SHA-256 of the archived text
f6528b994aed4f0a89951d5f6d25881dba217d47b7c8b26576eee469716dd181- Stable URL of this page
https://metraipolis.com/documento/dc_3dd72e2e60db
How to cite
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory — arXiv:2608.16889 — arXiv (en), https://arxiv.org/abs/2608.16889 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3dd72e2e60db (Metraipolis archive dc_3dd72e2e60db, sha256 f6528b994aed4f0a89951d5f6d25881dba217d47b7c8b26576eee469716dd181)
BibTeX
@misc{dc3dd72e2e60db,
title = {Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory — arXiv:2608.16889},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16889},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3dd72e2e60db; sha256 f6528b994aed4f0a89951d5f6d25881dba217d47b7c8b26576eee469716dd181},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16889. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-language-action (VLA) and world-action models (WAMs) increasingly master individual skills, yet the chain still fails: errors compound beyond the policy's ability to correct, and one subtask silently constrains the next. A promising pathway freezes the VLA and puts an LLM coding agent in charge: it plans in language, moves in free space with analytic primitives, invokes the VLA only for contact-rich segments, and writes adaptation into language memory. Yet applied to long horizons, this recipe breaks twice. (1) Its competence comes from whole-task exploration at test time, whose cost is exponential in the number of stages: if one stage needs T episodes, a K-stage task needs on the order of T^K, and a failure does not reveal which stage caused it. (2) It has no representation of transitions: the VLA primitive carries an exit but no entry condition, and a subtask can succeed in a form its successor cannot use. We present BATON to address both failures. Against (1), BATON makes the subtask the unit of exploration: each subtask is explored in the cheap short-horizon regime and its solution stored in memory; a long-horizon trajectory is then composed from these solutions rather than discovered whole. Exploration cost becomes linear (KT), and each failure is attributed to one stage. Against (2), BATON equips exploration with a transition-aware memory. Within a subtask, a verifier agent governs the invocation transition: the VLA is invoked only after the wrist view confirms the scene is ready. Across subtasks, a handoff transition restores an entry state disturbed by the predecessor's residue, and a lookahead transition selects the strategy whose outcome the successor can inherit. On the RoboMemArena benchmark, BATON improves task success by 37.7% and cumulative success by 29.7% over the SoTA. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.16889 — 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 2026-10-18T16:29:14.167Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).