Metraipolis › archive › dc_0ee3e6efdafd
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments — arXiv:2609.15364
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15364
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:47:58.176Z
- SHA-256 of the archived text
97135cc5a99aab453ebbabdd70621ea7de1da5b8a44118a8220c2c773c5f1242- Stable URL of this page
https://metraipolis.com/documento/dc_0ee3e6efdafd
How to cite
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments — arXiv:2609.15364 — arXiv (en), https://arxiv.org/abs/2609.15364 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ee3e6efdafd (Metraipolis archive dc_0ee3e6efdafd, sha256 97135cc5a99aab453ebbabdd70621ea7de1da5b8a44118a8220c2c773c5f1242)
BibTeX
@misc{dc0ee3e6efdafd,
title = {RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments — arXiv:2609.15364},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15364},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ee3e6efdafd; sha256 97135cc5a99aab453ebbabdd70621ea7de1da5b8a44118a8220c2c773c5f1242},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15364. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce \textbf{RSIAgent}, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction. RSIAgent coordinates curriculum, actor, and verifier agents to continually explore the environment, validate outcomes, and retain environment-specific knowledge, including reusable causal relationships between actions, conditions, and consequences. It further adopts a \textbf{broad-then-deep} exploration strategy, combining parallel broad recursive self-exploration for discovering diverse environment structures with focused deep self-exploration for uncovering hard cases, hidden constraints, boundary conditions, and previously unknown causal dependencies. The resulting memory is frozen and can be directly reused for downstream tasks without updating model parameters. Experiments on OSWorld-v2 and Agent's Last Exam show that RSIAgent substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.15364 — 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 2026-10-15T22:29:03.308Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).