chipbench-9aa46682·2 events·first seen Aliases: ChipBench
HORIZON is a new agentic framework that treats hardware design as repository-level code evolution, using a Markdown harness compiled into a project pack with domain knowledge, evaluator, and git/runtime policy. A hands-free agent loop evolves an isolated git worktree, extending prior self-evolution work from EDA software to hardware design artifacts. The system achieves 100% benchmark completion across ChipBench, RTLLM, Verilog-Eval, and nine CVDP categories, though the authors caution these are controlled proxies and the broader chip design problem remains unsolved.
Import AI issue 444 covers multiple AI/ML topics including LLM-based societies (multi-agent simulation research), Huawei's use of AI for kernel development, and ChipBench, a benchmark for evaluating AI on chip design tasks. The newsletter also touches on quantifying creativity as a research question. As a tier-2 commentary digest, it aggregates several distinct technical threads rather than reporting a single primary development.