Metraipolis › archive › dc_ae2e165fafb7
Towards Robust Long-Lived Agents: Benchmarking Experience Lifecycles in Evolving Environments — arXiv:2611.05450
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05450
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:16:34.330Z
- SHA-256 of the archived text
af55786e8344362daa07261e5caa92186ab983efb262169ca9ecc0eb216062af- Stable URL of this page
https://metraipolis.com/documento/dc_ae2e165fafb7
How to cite
Towards Robust Long-Lived Agents: Benchmarking Experience Lifecycles in Evolving Environments — arXiv:2611.05450 — arXiv (en), https://arxiv.org/abs/2611.05450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae2e165fafb7 (Metraipolis archive dc_ae2e165fafb7, sha256 af55786e8344362daa07261e5caa92186ab983efb262169ca9ecc0eb216062af)
BibTeX
@misc{dcae2e165fafb7,
title = {Towards Robust Long-Lived Agents: Benchmarking Experience Lifecycles in Evolving Environments — arXiv:2611.05450},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05450},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae2e165fafb7; sha256 af55786e8344362daa07261e5caa92186ab983efb262169ca9ecc0eb216062af},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As agents become more capable, they are moving beyond one-off tasks toward sustained assistance across successive user goals. Such assistance requires agents to discover how unfamiliar environments work, reuse what they learn across tasks, and keep that experience current as environments evolve. Existing benchmarks increasingly study experience reuse and adaptation, but provide limited insight into which parts of accumulated experience agents revise, retain, or lose. To address this gap, we introduce ReScopeBench, a benchmark for the experience lifecycle across 18 interactive environments. It distinguishes structural experience about how an environment is organized and accessed from rule experience about reusable principles and constraints that guide decisions across tasks. To study how experience is acquired, reused, and revised, we propose an experience-first construction approach. It builds task streams around shared experience and introduces silent environmental changes. We evaluate task performance and track changes in saved experience throughout each stream. Across 20 models, we find that retained experience improves task performance, but agents struggle to keep it current as environments change. Even when the required experience is correctly recorded, agents do not always complete tasks successfully. These findings identify selective maintenance and effective use as complementary challenges for long-lived agents. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.05450 — 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 2026-11-05T18:12:48.986Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).