Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization
cs.AI, cs.AR
Submitted: 2026-04-28
Updated: 2026-10-12
Code: https://github.com/MoonshotAI/Kimi-K2.5
Terminology
Sources
- CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
- AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
- Barbarians at the Gate: How AI is Upending Systems Research
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- The Championship Simulator: Architectural Simulation for Education and Competition
- ArchAgent: Agentic AI-driven Computer Architecture Discovery
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research
- Illuminating search spaces by mapping elites
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Computer Architecture's AlphaZero Moment: Automated Discovery in an Encircled World
- EvoTorch: Scalable Evolutionary Computation in Python
- ThetaEvolve: Test-time Learning on Open Problems
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems