跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-15AI 評分68

論文提出 Athanor,一個面向自主後訓練研究的智能體原生系統

Athanor: An Agent-Native System for Autonomous Post-Training Research

AI 導讀

Athanor 論文介紹一個開放的智能體原生研究系統,並展示四個 Claude Opus 5.5 智能體在 104 小時內自主後訓練 Qwen3-4B-Base,使其平均表現追平或超越官方指令微調版本。

正文

Published on Oct 15

Authors:

,

,

,

,

,

,

Abstract

A team of autonomous AI agents used an open research system to independently post-train a small base model into a cross-domain generalist that matched or exceeded its official instruction-tuned version.

Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence. We study a weaker form that can be measured today: frontier agents post-training a small raw base model with public data, as a test of their research potential. We build Athanor, an open agent-native system for autonomous post-training research (AutoPostTrain) on real GPUs. We give the agents full research autonomy, low-friction engineering tools, and efficient starter code. The agents carry out the research themselves: they read datasets and evaluation results, build their training data, write and modify training algorithms, tune hyperparameters, and analyze the results to decide what to try next. They work in a sandbox and cannot use external teacher models. Athanor's services supply frozen evaluation, managed jobs, decontaminated data, a persistent research record, and a held-out suite the agents are unaware of. In a 104-hour campaign, a team of four Claude Opus 5.5 agents, each on an eight-GPU node and given no research advice, improves Qwen3-4B-Base from 15.9 to 67.3 on a six-task development suite and from 9.2 to 48.2 on a held-out suite, against 66.5 and 47.9 for the official Qwen3-4B-Instruct-2507. To our knowledge, this is the first demonstration that a team of frontier agents can autonomously post-train a raw base model into a cross-domain generalist model that matches or surpasses the official instruct version on average. The campaign's full record shows that the agents reach this level by recombining known methods and each other's models: SFT on public reasoning data, RL with a rollout change one agent introduced, weight merges across agents, and rounds of self-distillation. With execution handled, today's agents already have the engineering and research ability to conquer this task. We hope Athanor provides a foundation for scaling autonomous AI research.

View arXiv page View PDF Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.21055 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/2610.21055 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/2610.21055 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