#automated-design News & Analysis

4 articles tagged with #automated-design. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · Apr 77/10

🧠

Evolutionary Search for Automated Design of Uncertainty Quantification Methods

Researchers developed an LLM-powered evolutionary search method to automatically design uncertainty quantification systems for large language models, achieving up to 6.7% improvement in performance over manual designs. The study found that different AI models employ distinct evolutionary strategies, with some favoring complex linear estimators while others prefer simpler positional weighting approaches.

🧠 Claude🧠 Sonnet🧠 Opus

AIBullisharXiv – CS AI · Feb 277/109

🧠

ArchAgent: Agentic AI-driven Computer Architecture Discovery

ArchAgent, an AI-driven system built on AlphaEvolve, has achieved breakthrough results in automated computer architecture discovery by designing state-of-the-art cache replacement policies. The system achieved 5.3% performance improvements in just 2 days and 0.9% improvements in 18 days, working 3-5x faster than human-developed solutions.

AINeutralarXiv – CS AI · Jun 236/10

🧠

AutoRAS: Learning Robust Agentic Systems with Primitive Representations

Researchers introduce AutoRAS, a framework for automatically designing robust multi-agent AI systems that maintain performance under adversarial attacks. The approach uses symbolic primitives to encode agent structure and behavior, optimizing for both task success and system resilience rather than treating robustness as an afterthought.

AINeutralarXiv – CS AI · Jun 235/10

🧠

An LLM-Orchestrated Agent for Directional-Coupler Design with Self-Consistent Eigenmode and FDTD Validation

Researchers present an LLM-based design agent that orchestrates the optimization of silicon-on-insulator directional couplers by coordinating eigenmode solvers and FDTD simulations without performing calculations itself. The agent achieved a 50/50 optical splitter with 0.498 cross-fraction accuracy against a 0.500 target, demonstrating effective human-AI collaboration in photonic device engineering.