物理约束基础模型的智能体演化
Agentic evolution of physically constrained foundation models
AI总结：
提出基于演化知识图谱的多智能体发现引擎，自动设计硬件兼容计算系统，在基础模型部署中演化出超越人工的压缩方法，实现大规模模型高效部署。
摘要：
人工智能日益推动自动化科学发现，但当代通用智能体缺乏物理基础，经常产生与硬件不兼容的设计。本文提出一个物理基础的多智能体发现引擎，能够自主构建符合硬件要求的计算系统。该框架以结构化过去科学创新的演化知识图谱为基础，提取“算法思维链”，将盲目的随机搜索转化为有导向的结构演化。应用于基础模型部署的极端测试场景，该引擎演化出两种超越人工启发式方法的硬件感知压缩方法：Q-Enhance缓解了密集模型的长上下文精度损失，MoE-Salient-AQ在亚3比特条件下比最先进的手工稀疏混合专家设计提升3.7%。利用带宽高效的敏感度剖面，我们成功将庞大的2350亿参数模型部署到受限的双A100服务器上，内存需求减少75%，精度仅下降0.64%。通过将无约束的组合搜索转化为知识驱动的自主演化，这为在严格物理边界内实现机器驱动的发现建立了一种可扩展的硬件-软件协同设计范式。
英文摘要：
Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatible designs. Here, we present a physically grounded, multi-agent discovery engine that autonomously architects hardware-compliant computing systems. Anchored by an Evolutionary Knowledge Graph structuring past scientific innovations, the framework extracts an "algorithmic Chain-of-Thought" to transform blind stochastic search into directed structural evolution. Applied to the extreme testbed of foundation model deployment, the engine evolved two hardware-aware compression methodologies surpassing human-engineered heuristics: Q-Enhance mitigates long-context accuracy loss in dense models, and MoE-Salient-AQ outperforms state-of-the-art manual sparse Mixture-of-Experts designs by 3.7% at sub-3-bit regimes. Utilizing a bandwidth-efficient Sensitivity Profile, we successfully deployed a massive 235-billion-parameter model onto a constrained dual-A100 server, reducing memory requirements by 75% with a marginal 0.64% accuracy degradation. By transforming unconstrained combinatorial search into knowledge-driven autonomy, this establishes a scalable hardware-software co-design paradigm for machine-driven discovery within strict physical boundaries.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
