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

• URL: http://arxiv.org/abs/2512.22435v1
• Date: Sat, 27 Dec 2025 02:06:05 GMT
• Title: AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded Experience
• Abstract summary: We propose AnalogSAGE, an open-source multi-agent framework that coordinates three-stage agent explorations through four stratified memory layers.<n>Our benchmark spans ten specification-driven operational amplifier design problems of varying difficulty, enabling quantitative and cross-task comparison.<n> AnalogSAGE achieves a 10$times$ overall pass rate, a 48$times$ Pass@1, and a 4$times$ reduction in parameter search space compared with existing frameworks.
• Score: 13.371317989669782
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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$\times$ overall pass rate, a 48$\times$ Pass@1, and a 4$\times$ 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.

Related papers

• EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Models [20.30914242698969]
  EXPLORE is a framework that integrates simulator-guided Monte Carlo Tree Search (MCTS) with transformer-based decoding to enable test-time scaling for analog topology generation.<n>On a 6-component benchmark at a tight tolerance of 0.01, EXPLORE raises the success rate from 12% for one-shot generation and 33% for a sampling-and-filter baseline to 65%, and MSE by over 20% relative to sampling-and-filter under the same search budget.
  arXiv  Detail & Related papers  (2026-07-15T03:35:14Z)
• AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents [23.16076070830351]
  We propose AnalogAgent, a training-free agentic framework for analog circuit design automation.<n>Across established benchmarks, AnalogAgent achieves 92% Pass@1 with Gemini and 97.4% Pass@1 with GPT-5.<n>With compact models, it yields a +48.8% average Pass@1 gain across tasks and reaches 72.1% Pass@1 overall.
  arXiv  Detail & Related papers  (2026-03-25T03:59:02Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems [51.2882705779387]
  Cloud-OpsBench is a large-scale benchmark that employs a State Snapshot Paradigm to construct a deterministic digital twin of the cloud.<n>It features 452 distinct fault cases across 40 root cause types spanning the full stack.
  arXiv  Detail & Related papers  (2026-02-28T05:04:42Z)
• How to Set the Learning Rate for Large-Scale Pre-training? [73.03133634525635]
  We formalize this investigation into two distinct research paradigms: Fitting and Transfer.<n>Within the Fitting Paradigm, we introduce a Scaling Law for search factor, effectively reducing the search complexity from O(n3) to O(n*C_D*C_) via predictive modeling.<n>We extend the principles of $$Transfer to the Mixture of Experts (MoE) architecture, broadening its applicability to encompass model depth, weight decay, and token horizons.
  arXiv  Detail & Related papers  (2026-01-08T15:55:13Z)
• Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs [49.66344956133349]
  Reasoning capacity shapes both inference-time performance and reinforcement learning (RL) training for large (vision-) language models.<n>This paper proposes Reasoning Palette, a novel latent-modulation framework that endows the model with a latent variable for strategic contextualization.
  arXiv  Detail & Related papers  (2025-12-19T03:32:53Z)
• Dense Associative Memories with Analog Circuits [4.0086293309536405]
  We propose a general method for building analog accelerators for DenseAMs.<n>We find that analog DenseAM hardware performs inference in constant time independent of model size.<n>We estimate lower bounds on the achievable time constants imposed by amplifier specifications, suggesting that even conservative existing analog technology can enable inference times on the order of tens to hundreds of nanoseconds.
  arXiv  Detail & Related papers  (2025-12-17T01:22:44Z)
• SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation [24.019381388104236]
  We propose SCoTER, a unified framework that treats pattern discovery and structure-aware transfer as a jointly optimized problem.<n>Specifically, SCoTER operationalizes this through two synergistic components: a GVM pipeline for automated pattern discovery and a structure-preserving integration architecture that transfers stepwise logic to efficient models.
  arXiv  Detail & Related papers  (2025-11-24T03:00:04Z)
• ZeroSim: Zero-Shot Analog Circuit Evaluation with Unified Transformer Embeddings [36.00558662624576]
  ZeroSim is a transformer-based performance modeling framework designed to achieve robust in-distribution generalization across trained topologies.<n>We show that ZeroSim significantly outperforms baseline models such as multilayer perceptrons, graph neural networks and transformers.<n>When integrated into a reinforcement learning-based parameter optimization pipeline, ZeroSim achieves a remarkable speedup (13x) compared to conventional SPICE simulations.
  arXiv  Detail & Related papers  (2025-11-10T22:08:30Z)
• AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing [1.2617078020344616]
  A novel agentic AI framework for sample-efficient and explainable analog circuit sizing is presented.<n>The AnaFlow framework is demonstrated for two circuits of varying complexity and is able to complete the sizing task fully automatically.<n>The inherent explainability makes this a powerful tool for analog design space exploration and a new paradigm in analog EDA.
  arXiv  Detail & Related papers  (2025-11-05T18:24:01Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• AnalogSeeker: An Open-source Foundation Language Model for Analog Circuit Design [20.332984809384445]
  We propose AnalogSeeker, an effort toward an open-source foundation language model for analog circuit design.<n>High-quality, accessible textbooks across relevant subfields are systematically curated and cleaned into a textual domain corpus.<n>In practice, we train the Qwen2.5-32B-Instruct model to obtain AnalogSeeker, which achieves 85.04% accuracy on AMSBench-TQA.
  arXiv  Detail & Related papers  (2025-08-14T07:32:07Z)
• CROP: Circuit Retrieval and Optimization with Parameter Guidance using LLMs [5.611060564629618]
  We present CROP, the first large language model (LLM)-powered automatic VLSI design flow tuning framework.<n>Our approach includes: (1) a scalable methodology for transforming RTL source code into dense vector representations, (2) an embedding-based retrieval system for matching designs with semantically similar circuits, and (3) a retrieval-augmented generation (RAG)-enhanced LLM-guided parameter search system.<n>Experiment results demonstrate CROP's ability to achieve superior quality-of-results (QoR) with fewer iterations than existing approaches on industrial designs, including a 9.9% reduction in power consumption.
  arXiv  Detail & Related papers  (2025-07-02T20:25:47Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [58.05959902776133]
  We introduce Single-Pass.<n>with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation.<n>We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP)<n>On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $sim$16% of training samples compared to human-labeled and other synthetically trained baselines.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.