跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 28 天前AI 評分57

ParetoRSI-Gym:AI 智能體能否跨多個領域改進語言模型?

ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?

AI 導讀

ParetoRSI-Gym 評估遞歸自我改進智能體能否透過整理數據與訓練,提升語言模型在多個領域的泛化表現。Claude Code 配合 Opus-5 的 proxy-best checkpoint 泛化分數,按三個基礎模型和五個領域等權平均,較起始模型提升 9.2%(絕對提升 2.3 點);單一領域最高相對提升 63%,出現在 Ministral-3-3B 的醫學領域。

正文

Published on Oct 25

Authors:

,

,

,

,

,

,

,

Abstract

ParetoRSI-Gym evaluates recursive self-improvement agents across multiple domains by fixing the model and pipeline while allowing data curation and training loops, revealing significant generalization gains and distinct agent strategies.

Recursive self-improvement (RSI) requires an agentic system to design, train, and evaluate its own successor. Data-driven post-training is a central part of that loop, yet existing evaluations measure it on a single benchmark, where an agent selects from a static pool or distills a stronger model to push one score up in one run. Real post-training is multi-domain, and a gain in one domain has to be weighed against a regression in another. We propose ParetoRSI-Gym, in which an agent searches for data, curates it, trains, reads back per-domain results, and repeats, with everything but the data held fixed: the initial LLM, the five domains (math, code, finance, medicine, science), the toolset, and the SFT pipeline. Generalization benchmarks in each domain separate capability gains from overfitting to the scores the agent optimizes against. Across three agent systems, three base models, five rounds and multiple seeds, the strongest system, Claude Code with Opus-5, raises the generalization scores of its proxy-best checkpoint by 9.2% relative to the starting model (+2.3 absolute points), averaged with equal weight over three base models and five domains, with a single-domain relative gain of up to 63% (medicine on Ministral-3-3B). Further analysis shows that the harness matters as much as the model it drives, and that each agent keeps a unique data selection strategy. We see our work as a step towards evaluation of RSI systems in real-world machine learning engineering.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.34386

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.34386 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.34386 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.34386 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co