NVIDIA 论文提出 Agora，把每条结果、假设和验证记录为不可变的 Git 提交，让多个编码智能体不再重复彼此的实验，并能基于他人已验证的结果继续推进。论文报告了一次近 12 天的运行：13 个 LLM worker 在没有任务分配和中央规划者的情况下，从 141 个捐赠模型初始化一个 119.6M 参数的混合模型，这些模型没有匹配的 donor，且无训练数据和梯度更新。
NVIDIA 这篇论文给出多智能体科研协作的具体组织方式，读者可了解它如何用 Git 记录结果与验证来减少重复实验。
Banger paper from NVIDIA on shared memory for research agents.
(bookmark it)
If you run several coding agents on the same research problem, this design keeps them from repeating each other's experiments and lets each agent build on results the others have already verified.
Agora records every result, hypothesis and verification as an immutable Git commit.
Parent edges show what each claim builds on, and an index lists open branches and which claims have been verified.
They ran 13 LLM workers for nearly 12 days without assigned tasks or a central planner. The workers had to initialize a 119.6M-parameter hybrid model from 141 donor models without training data or gradient updates.
The workers posted 1,703 contributions.
They cut the evaluator from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M. All 165 independent reproductions succeeded.
Paper: https://t.co/IujsIvVeUO
Chat with Paper: https://t.co/yf5P8GgnJo
来源：@omarsar0 · x.com