LLM-FSM: Scaling Large Language Models for Finite-State Reasoning in RTL Code Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Yuheng, Gokmen, Berk, Xie, Zhouhua, Li, Peijing, Trippel, Caroline, Raina, Priyanka, Tambe, Thierry
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910014495522816
author Wu, Yuheng
Gokmen, Berk
Xie, Zhouhua
Li, Peijing
Trippel, Caroline
Raina, Priyanka
Tambe, Thierry
author_facet Wu, Yuheng
Gokmen, Berk
Xie, Zhouhua
Li, Peijing
Trippel, Caroline
Raina, Priyanka
Tambe, Thierry
contents Finite-state reasoning, the ability to understand and implement state-dependent behavior, is central to hardware design. In this paper, we present LLM-FSM, a benchmark that evaluates how well large language models (LLMs) can recover finite-state machine (FSM) behavior from natural-language specifications and translate it into correct register transfer-level (RTL) implementations. Unlike prior specification-to-RTL benchmarks that rely on manually constructed examples, LLM-FSM is built through a fully automated pipeline. LLM-FSM first constructs FSM with configurable state counts and constrained transition structures. It then prompts LLMs to express each FSM in a structured YAML format with an application context, and to further convert that YAML into a natural-language (NL) specification. From the same YAML, our pipeline synthesizes the reference RTL and testbench in a correct-by-construction manner. All 1,000 problems are verified using LLM-based and SAT-solver-based checks, with human review on a subset. Our experiments show that even the strongest LLMs exhibit sharply declining accuracy as FSM complexity increases. We further demonstrate that training-time scaling via supervised fine-tuning (SFT) generalizes effectively to out-of-distribution (OOD) tasks, while increasing test-time compute improves reasoning reliability. Finally, LLM-FSM remains extensible by allowing its FSM complexity to scale with future model capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07032
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLM-FSM: Scaling Large Language Models for Finite-State Reasoning in RTL Code Generation
Wu, Yuheng
Gokmen, Berk
Xie, Zhouhua
Li, Peijing
Trippel, Caroline
Raina, Priyanka
Tambe, Thierry
Artificial Intelligence
Hardware Architecture
Computation and Language
Finite-state reasoning, the ability to understand and implement state-dependent behavior, is central to hardware design. In this paper, we present LLM-FSM, a benchmark that evaluates how well large language models (LLMs) can recover finite-state machine (FSM) behavior from natural-language specifications and translate it into correct register transfer-level (RTL) implementations. Unlike prior specification-to-RTL benchmarks that rely on manually constructed examples, LLM-FSM is built through a fully automated pipeline. LLM-FSM first constructs FSM with configurable state counts and constrained transition structures. It then prompts LLMs to express each FSM in a structured YAML format with an application context, and to further convert that YAML into a natural-language (NL) specification. From the same YAML, our pipeline synthesizes the reference RTL and testbench in a correct-by-construction manner. All 1,000 problems are verified using LLM-based and SAT-solver-based checks, with human review on a subset. Our experiments show that even the strongest LLMs exhibit sharply declining accuracy as FSM complexity increases. We further demonstrate that training-time scaling via supervised fine-tuning (SFT) generalizes effectively to out-of-distribution (OOD) tasks, while increasing test-time compute improves reasoning reliability. Finally, LLM-FSM remains extensible by allowing its FSM complexity to scale with future model capabilities.
title LLM-FSM: Scaling Large Language Models for Finite-State Reasoning in RTL Code Generation
topic Artificial Intelligence
Hardware Architecture
Computation and Language
url https://arxiv.org/abs/2602.07032