# IBM reports lower inference costs for AI-led chip optimization

_Published Tuesday, October 13, 2026 at 8:09 AM EDT · AI, Science · Latest · Tier 2 — Notable_

![IBM reports lower inference costs for AI-led chip optimization — Primary](https://research.ibm.com/_next/image?url=https%3A%2F%2Fresearch-website-prod-cms-uploads.s3.us.cloud-object-storage.appdomain.cloud%2Fhardware_green_d92a166da5.png&w=1200&q=85)

IBM Research reports that agents using open models optimized a quantum error correction hardware design to deliver a 52-times speedup in high-level synthesis estimates for approximately $26 in inference cost. Under the same 100-hypothesis search budget, a proprietary-model configuration achieved a 204x speedup for $299.

A coordinator directed four worker agents to modify the design, using correctness checks and synthesis results to guide further experiments. The open models ran on premises through llm-d, which reuses shared context and allocates prompt processing and token generation separately.

The open-model search produced the smallest area design. Each configuration received only one search run, and the cost comparison covers inference; evaluation of the complete workflow must also account for synthesis and verification costs.

## Sources

- [IBM Research](https://research.ibm.com/blog/open-agent-factories-and-distributed-inference-for-chip-design)

---
Canonical: https://techandbusiness.org/newswire/ay7cZygsQ9VDTgRl5sLEeb
Published: 2026-10-13T12:09:37.713Z
Story chronology: 2026-10-13T12:00:00.000Z
Retrieved: 2026-10-13T14:48:29.684Z
Publisher: Tech & Business (techandbusiness.org)