arXiv cs.MA· Yufa Zhou, Yichen Wang, Jiakun Fan, Ziqi Shu, Zhichao Liu, Anru R. Zhang, Neiwen Ling, Zijun Wei·· 2 天前AI 评分71
Athanor：面向自主后训练研究的智能体原生系统
Athanor: An Agent-Native System for Autonomous Post-Training Research
AI 导读
研究者提出 Athanor，一个在真实 GPU 上运行的智能体原生自主后训练研究系统（AutoPostTrain），让智能体自行读取数据集与评测结果、构建训练数据、修改训练算法并调参。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.21055 [cs.AI] |
| (or arXiv:2610.21055v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21055 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yufa Zhou [view email]
[v1]
Thu, 15 Oct 2026 00:56:33 UTC (638 KB)
来源：arXiv cs.MA · arxiv.org