Metraipolis › archive › dc_a015f20bb2d5
Ask to Evolve: A Unified Harness for Lifelong Embodied Navigation with Hybrid Action Space and Persistent Memory — arXiv:2610.39446
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39446
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:44:26.510Z
- SHA-256 of the archived text
1005f254b5027ea645e31d19d5ad147a78a61292b62005e1a45cf00b2c898318- Stable URL of this page
https://metraipolis.com/documento/dc_a015f20bb2d5
How to cite
Ask to Evolve: A Unified Harness for Lifelong Embodied Navigation with Hybrid Action Space and Persistent Memory — arXiv:2610.39446 — arXiv (en), https://arxiv.org/abs/2610.39446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a015f20bb2d5 (Metraipolis archive dc_a015f20bb2d5, sha256 1005f254b5027ea645e31d19d5ad147a78a61292b62005e1a45cf00b2c898318)
BibTeX
@misc{dca015f20bb2d5,
title = {Ask to Evolve: A Unified Harness for Lifelong Embodied Navigation with Hybrid Action Space and Persistent Memory — arXiv:2610.39446},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39446},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a015f20bb2d5; sha256 1005f254b5027ea645e31d19d5ad147a78a61292b62005e1a45cf00b2c898318},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Giving embodied agents the freedom to act autonomously, initiate interactions, and understand their surroundings through experience is a step toward bringing them to life in the physical world. Realizing this vision requires action, interaction, and memory to work together, so that each encounter can inform current decisions and contribute experience for future tasks. We present EvoLife, a unified navigation harness that enables a multimodal embodied agent to choose how to move, when to ask, and what experience to carry forward. Its hybrid action space supports waypoint navigation, local discrete adjustments, pixel-based navigation, and object-directed navigation. Active interaction allows the agent to seek clarification or assistance when it encounters ambiguity or difficulty, while persistent spatial memory binds observations and dialogue to places, retaining useful experience to guide subsequent visits. We evaluate eight benchmarks across four task families: vision-language navigation, object navigation, interactive instance navigation, and continuous multi-task navigation. With an average of only 1.87 active interactions per episode, our method achieves a first-visit success rate (SR) of 100% across four 100-episode sets spanning vision-language navigation and object navigation. Complete-sequence SR reaches 98% on 50 LHPR-VLN sequences and 94% on 50 GOAT-Bench sequences. In the R2R revisit setting, success weighted by path length (SPL) increases from 82.23% to 93.31% with retained experience. Multi-day physical navigation further demonstrates exploration, proactive help-seeking, and revisiting remembered places. Together, these results advance the vision of bringing embodied agents to life through autonomous action, proactive interaction, and the accumulation and reuse of experience. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.39446 — 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 2026-11-01T02:16:58.660Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).