mlsanityData to 14 Oct 2026

ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development

arXiv 2504.19144 ↗First posted 27 Apr 2025cs.AI cs.AR cs.SEcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

The growing demand for Domain-Specific Architecture (DSA) has driven the development of Agile Hardware Development Methodology (AHDM). Hardware Construction Language (HCL) like Chisel offers high-level abstraction features, making it an ideal language for HCL-Based AHDM. While Large Language Models (LLMs) excel in code generation tasks, they still face challenges with Chisel generation, particularly regarding syntax correctness and design variability. Recent reasoning models have significantly enhanced code generation capabilities through test-time scaling techniques. However, we found that reasoning models without domain adaptation cannot bring substantial benefits to Chisel code generation tasks. This paper presents ChiseLLM, a solution comprising data processing and transformation, prompt-guided reasoning trace synthesis, and domain-adapted model training. We constructed high-quality datasets from public RTL code resources and guided the model to adopt structured thinking patterns through prompt enhancement methods. Experiments demonstrate that our ChiseLLM-7B and ChiseLLM-32B models improved syntax correctness by 18.85% and 26.32% respectively over base models, while increasing variability design ability by 47.58% compared to baseline reasoning models. Our datasets and models are publicly available, providing high-performance, cost-effective models for HCL-Based AHDM, and offering an effective baseline for future research. Github repository: https://github.com/observerw/ChiseLLM

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 13 of its 53 references that are in the map. First posted on arXiv 27 Apr 2025.

Builds on

13 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025S*: Test Time Scaling for Code Generation20 Feb
  2. 2024Qwen2.5-Coder Technical Report18 Sep
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code12 Mar

Other references · 10

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  5. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  6. 2024DeepSeek-V3 Technical Reportcited by 811
  7. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 137
  8. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  9. 2023ChipGPT: How far are we from natural language hardware designcited by 105
  10. 2024BetterV: Controlled Verilog Generation with Discriminative Guidancecited by 100

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
  2. 2025QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
  3. 2025ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection
  4. 2026How LLMs Fail and Generalize in RTL Coding for Hardware Design?
  5. 2025Towards LLM-based Root Cause Analysis of Hardware Design Failures
  6. 2026LLM4RTL: Tool-Assisted LLM for RTL Generation
  7. 2025When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generation
  8. 2025SysVCoder: An LLM-Driven Framework for Systematic Generation of System-Level Design