IBM ResearchResearch
Scaling AI-driven chip design with open agent factories

Open models and llm-d enabled IBM Research to explore quantum error correction hardware at 11.5× lower inference cost than an all-proprietary configuration.
Read at IBM Research ↗Related
Voices#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI Lex Fridman Podcast

GitHubScaling Git for the agentic software factory GitLab Blog

ToolsImprove TTFT for Multi-Turn Agentic Workloads with Bi-Directional KV Transfer in vLLM vLLM Blog

VoicesWhy agent swarms could be the next “scaling law” Understanding AI

ToolsVM Sandboxes: Full computers for agents Modal
