# RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation

arXiv: https://arxiv.org/abs/2604.24218 · HTML: https://mlsanity.com/paper/2604.24218/

## 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 20 of its 36 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 20 of 20)

- [ChipNeMo: Domain-Adapted LLMs for Chip Design](https://mlsanity.com/paper/2311.00176/) (2023)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [Benchmarking Large Language Models for Automated Verilog RTL Code Generation](https://mlsanity.com/paper/2212.11140/) (2022)
- [The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2305.14045/) (2023)
- [TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation](https://mlsanity.com/paper/2402.10178/) (2024)
- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset](https://mlsanity.com/paper/2410.22457/) (2024)
- [UVLLM: An Automated Universal RTL Verification Framework using LLMs](https://mlsanity.com/paper/2411.16238/) (2024)
- [Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation](https://mlsanity.com/paper/2502.10857/) (2025)
- [FIXME: Towards End-to-End Benchmarking of LLM-Aided Design Verification](https://mlsanity.com/paper/2507.04276/) (2025)
- [AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation](https://mlsanity.com/paper/2507.19902/) (2025)
- [A Comprehensive Survey of AI-Driven Advancements and Techniques in Automated Program Repair and Code Generation](https://mlsanity.com/paper/2411.07586/) (2024)
- [Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks](https://mlsanity.com/paper/2501.06625/) (2025)
- [iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs](https://mlsanity.com/paper/2505.22086/) (2025)
- [ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection](https://mlsanity.com/paper/2505.19734/) (2025)
- [ChatModel: Automating Reference Model Design and Verification with LLMs](https://mlsanity.com/paper/2506.15066/) (2025)
- [ChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs](https://mlsanity.com/paper/2604.02811/) (2026)
- [ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications](https://mlsanity.com/paper/2512.05371/) (2025)
- [Towards Practical and Useful Automated Program Repair for Debugging](https://mlsanity.com/paper/2407.08958/) (2024)

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

- [BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification](https://mlsanity.com/paper/2609.34785/) (2026)

## Abstract (arXiv)

As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models (typically written in SystemC) for early architecture exploration and verification. While Large Language Models (LLMs) show promise in code generation, their application to hardware modeling faces unique challenges: (1) Rigid, static workflows fail to adapt to varying design complexity, causing inefficiency; (2) Context window overflow in multi-turn interactions leads to catastrophic forgetting of critical specifications; and (3) the Coupled Validation Failure problem--where generated Testbenches (TBs) incorrectly validate flawed models due to correlated hallucinations--severely undermines reliability. To address these limitations, we introduce RefEvo, a dynamic multi-agent framework designed for agile and reliable reference modeling. RefEvo features three key innovations: (1) A Dynamic Design Planner that autonomously decomposes design specifications and constructs tailored execution workflows based on semantic complexity; (2) A Co-Evolutionary Verification Mechanism, which employs a Dialectical Arbiter to simultaneously rectify the model and verification logic against the specification (Spec) oracle, effectively mitigating false positives; and (3) A Spec Anchoring Strategy for lossless context compression. Evaluated on a diverse benchmark of 20 hardware modules, RefEvo achieves a 95% pass rate, outperforming static baselines by a large margin. Furthermore, our context optimization reduces token consumption by an average of 71.04%, achieving absolute savings of over 70,000 tokens per session for complex designs while maintaining 100% specification recall.