TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules
Summary
We present TACS-RF, a framework where an LLM coding agent (Claude Opus 4.8) semi-autonomously drives industry-standard EDA tools to design a 240-251 GHz sub-THz transmitter in 90 nm SiGe BiCMOS, marking a step toward a 'text-to-ASIC' future for RF/mmWave hardware design.
Similar Articles
@dair_ai: Great paper on scaling agent skills. It includes some great tips for keeping your agent skill library updated and runni…
Paper proposes Skill++, which rewrites only the name and description of incoming agent skills to prevent routing interference in growing skill libraries, raising full-skill selection from 36.4% to 76.3% across 731 skills, three benchmarks, five routers, and the Codex CLI harness.
A clause that lifted human investment to 67% (2011 lab study): in a new preprint's game, no AI seller invested
A new preprint (arXiv 2610.40961) pits frontier LLMs against each other in the classic hold-up game, finding that renegotiable options that boosted human investment to 67% in a 2011 lab study produced zero seller investment across 1,440 AI-agent games.
Prism
Prism is a new product described as "Cursor for hardware engineering," an AI-assisted tool aimed at hardware/EDA workflows.
When your coding agent says "tests passed," what do you actually check before accepting the work?
A developer building an independent verification prototype for coding agents shares two reproduced cases where pytest reported passing despite failing tests (exit status 0, config-based deselection) and asks the community how they verify agent-generated changes before accepting them.
@0xShoopy: Anthropic just dropped a 10-page PDF on building your own skill library - 8 layers to an agent that picks the right pro…
Anthropic released a 10-page PDF outlining an 8-layer framework for building a personal skill library that lets Claude agents automatically select the right procedure, cutting token usage from ~36K to ~3.9K per request.