Metraipolis › archive › dc_15aaf02cf1fc

MaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses — arXiv:2610.28201

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.28201
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:03.148Z
SHA-256 of the archived text
f4b9c829c3b93386f621d5bd6b7ef041bd371711d1d57c5de8a7756b2a3ec4d7
Stable URL of this page
https://metraipolis.com/documento/dc_15aaf02cf1fc

How to cite

MaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses — arXiv:2610.28201 — arXiv (en), https://arxiv.org/abs/2610.28201 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_15aaf02cf1fc (Metraipolis archive dc_15aaf02cf1fc, sha256 f4b9c829c3b93386f621d5bd6b7ef041bd371711d1d57c5de8a7756b2a3ec4d7)
BibTeX
@misc{dc15aaf02cf1fc,
  title = {MaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses — arXiv:2610.28201},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.28201},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_15aaf02cf1fc; sha256 f4b9c829c3b93386f621d5bd6b7ef041bd371711d1d57c5de8a7756b2a3ec4d7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28201. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive self-improvement (RSI) of agent harnesses has emerged as an effective approach to enhancing the capabilities of large language model (LLM) agents. By searching the harness space for a specific LLM on a given dataset, RSI can discover a harness tailored to the capabilities and behavioral characteristics of that model. However, such optimization often creates a strong coupling between the learned harness and its target LLM, limiting generalization across models and requiring substantial computational resources to adapt to new LLMs. Moreover, existing RSI methods typically optimize a harness using feedback from a single model and evaluate its generalization to other models only after training. This paradigm treats model differences primarily as a criterion for evaluating generalization rather than as valuable evidence for optimization. In this paper, we introduce a new perspective that treats models as data and places the harness at the center of optimization. Building on this perspective, we propose \textsc{MaD-RSI}, a framework that directly optimizes a shared harness across multiple heterogeneous LLMs by incorporating their diverse failure trajectories into the training process. Rather than assessing model differences only after optimization, \textsc{MaD-RSI} leverages these differences as training evidence to guide the self-improvement of a shared harness. Furthermore, we introduce a new evaluation framework with two complementary metrics designed to assess the effectiveness of harness optimization across models. Experiments across multiple datasets and LLMs demonstrate that \textsc{MaD-RSI} improves generalization over existing approaches while reducing training costs.

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/2610.28201 — 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 2026-10-21T07:05:43.473Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).