# AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded Experience

arXiv: https://arxiv.org/abs/2512.22435 · HTML: https://mlsanity.com/paper/2512.22435/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 9 of 9)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning](https://mlsanity.com/paper/2503.11951/) (2025)
- [CktGNN: Circuit Graph Neural Network for Electronic Design Automation](https://mlsanity.com/paper/2308.16406/) (2023)
- [Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management](https://mlsanity.com/paper/2510.06727/) (2025)
- [Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs](https://mlsanity.com/paper/2509.16204/) (2025)
- [AnalogGym: An Open and Practical Testing Suite for Analog Circuit Synthesis](https://mlsanity.com/paper/2409.08534/) (2024)
- [ZeroSim: Zero-Shot Analog Circuit Evaluation with Unified Transformer Embeddings](https://mlsanity.com/paper/2511.07658/) (2025)

## Built on by (most cited first, 1 of 1)

- [Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems](https://mlsanity.com/paper/2609.01286/) (2026)

## Abstract (arXiv)

Analog circuit design remains a knowledge- and experience-intensive process that relies heavily on human intuition for topology generation and device parameter tuning. Existing LLM-based approaches typically depend on prompt-driven netlist generation or predefined topology templates, limiting their ability to satisfy complex specification requirements. We propose AnalogSAGE, an open-source self-evolving multi-agent framework that coordinates three-stage agent explorations through four stratified memory layers, enabling iterative refinement with simulation-grounded feedback. To support reproducibility and generality, we release the source code. Our benchmark spans ten specification-driven operational amplifier design problems of varying difficulty, enabling quantitative and cross-task comparison under identical conditions. Evaluated under the open-source SKY130 PDK with ngspice, AnalogSAGE achieves a 10× overall pass rate, a 48× Pass@1, and a 4× reduction in parameter search space compared with existing frameworks, demonstrating that stratified memory and grounded reasoning substantially enhance the reliability and autonomy of analog design automation in practice.