AIARLGMAJun 24

Agentic evolution of physically constrained foundation models

arXiv:2606.2553219.4
Predicted impact top 23% in AI · last 90 daysOriginality Highly original
AI Analysis

For AI hardware deployment, this provides a scalable paradigm for automated hardware-software co-design under physical constraints, addressing the hallucination problem in generalist agents.

This work presents a physically grounded multi-agent discovery engine that autonomously designs hardware-compliant computing systems. It evolved two compression methods that outperform human-engineered heuristics, achieving a 75% memory reduction on a 235B-parameter model with only 0.64% accuracy loss.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes