Agentic evolution of physically constrained foundation models

arXiv 2606.25532 ↗First posted 24 Jun 2026cs.AI cs.AR cs.LGcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

also in 1 more

Mixture-of-experts → MoE in reinforcement learning and robotics

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 43 references that are in the map. First posted on arXiv 24 Jun 2026.

Builds on

21 of 43 references.

References · 21

2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
2022Competition-Level Code Generation with AlphaCodecited by 1,462
2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationcited by 591
2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 424
2023Atom: Low-bit Quantization for Efficient and Accurate LLM Servingcited by 272
2026Towards End-to-End Automation of AI Researchcited by 159
2020A Survey on Evolutionary Neural Architecture Searchcited by 142
2024Empowering Biomedical Discovery with AI Agentscited by 118

9 more

2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 90
2024Evaluating Quantized Large Language Modelscited by 77
2024SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Modelscited by 63
2024Multi-objective Evolution of Heuristic Using Large Language Modelcited by 54
2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 53
2025Jet-Nemotron: Efficient Language Model with Post Neural Architecture Searchcited by 41
2024SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphscited by 31
2025MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Designcited by 30
2024EvoPress: Accurate Dynamic Model Compression via Evolutionary Searchcited by 20

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way