Agents
Scaling AI-driven chip design with open agent factories
IBM Research has presented a new approach that scales AI‑driven chip design by employing open “agent factories,” lowering inference cost by 11.5 × compared to fully proprietary setups. The method enab
IBM Research has presented a new approach that scales AI‑driven chip design by employing open “agent factories,” lowering inference cost by 11.5 × compared to fully proprietary setups. The method enables efficient quantum error‑correction hardware and enhances overall AI‑hardware performance while keeping resource usage minimal. This work demonstrates how collaborative, open‑source tooling can accelerate the development of cutting‑edge AI chips.
Related
- How distributed inference keeps large AI models moving
- Granite 4.2 brings native reasoning to enterprise agents
- LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing
Source: IBM Research | 2026-10-13