NVIDIA 发布研究代理共享内存设计论文
Banger paper from NVIDIA on shared memory for research agents. (bookmark it) If you run several co...
NVIDIA 新的共享内存设计，能让多个研究代理协同工作，避免重复实验，效率很高。
NVIDIA 的 Agora 系统让 13 个 LLM 工作者在 12 天内完成 1703 次贡献，通过 Git 提交记录结果和验证，避免重复实验。该系统让 119.6M 参数混合模型从 141 个捐赠模型初始化，成功完成 165 次独立复现，将评估器比特率从 3.39 降低到 1.899，缩小与 GPT-2 124M 的差距 62%。
Banger paper from NVIDIA on shared memory for research agents. (bookmark it) If you run several co...
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: arxiv.org/abs/2609.18094 Chat with Paper: academy.dair.ai/papers/agora-g… 💬 0 🔄 0 ❤️ 3 👀 631 📊 2 ⚡
