Recent advances in large language models (LLMs) and autonomous agents are creating new opportunities for hardware design optimization. This paper examines three connected directions toward autonomous RTL and synthesis optimization: (1) Realistic benchmarking. We discuss reference-based and open-ended RTL optimization benchmarks that evaluate optimization opportunities under realistic EDA workflows. (2) Tool-grounded RTL optimization. We present Dr. RTL, a multi-agent framework that automates critical-path analysis, RTL rewriting, and implementation-level evaluation, while continuously improving through reusable optimization skills. Evaluated on 20 real-world RTL designs, Dr.~RTL achieves average WNS/TNS improvements of 21%/17% with a 6% area reduction over commercial synthesis. (3) Design-specific synthesis optimization. We explore agent-driven synthesis script tuning and the discovery of executable synthesis algorithms across intermediate representations, technology-independent optimization, and technology mapping. Finally, we envision AI-native design automation that jointly explores architectural, RTL, and EDA algorithm design spaces, guided by verification constraints and implementation feedback.
Figures & tables
Figure 1. Three connected directions toward autonomous RTL and synthesis optimization. Realistic benchmarking establishes evaluation settings, tool-grounded agents optimize RTL beyond synthesis, and synthesis optimization extends agentic search from flow tuning to algorithm discovery.
Figure 2. Two complementary RTL optimization evaluation settings. Reference-based evaluation measures improvements against human-optimized RTL references, while open-ended evaluation measures further PPA improvements on original human-written designs. Both settings assess implementation quality after synthesis and functional verification.
(a) Reference-based: RTL-OPT
Method
Func. Pass
> Subopt.
> Ref.
Single-Shot LLM
GPT-4o-mini
75.0%
19.4%
5.6%
Gemini-2.5
69.4%
30.6%
5.6%
DeepSeek V3
69.4%
27.8%
13.9%
DeepSeek R1
61.1%
41.7%
13.9%
(b) Open-ended: Original RTL
Table 1. Comparison of LLM-based RTL optimization under (a) reference-based and (b) open-ended evaluation settings.
Figure 3. Overview of Dr. RTL. The framework coordinates critical-path analysis, parallel RTL rewriting, and tool-based evaluation. Commercial synthesis provides implementation feedback, while sequential equivalence checking verifies functional correctness.
Figure 4. Dr. RTL automates RTL PPA optimization through closed-loop interaction with EDA tools and distills optimization trajectories into reusable skills for continual self-improvement.
Figure 5. Optimization trajectories of Dr. RTL across iterations for two designs (router and pcie). WNS, TNS, area, and optimization score improve over successive iterations while preserving functional equivalence. The skill-enhanced variant converges faster and achieves better PPA than the variant without learned skills.
Figure 6. Distilling hierarchical optimization trajectories into a reusable skill library. Trajectories are organized across iterations, parallel candidates, and critical paths, supporting the extraction of optimization strategies with different confidence levels and associated transformation templates.
Figure 7. Our two levels of agentic synthesis optimization: script tuning for the commercial tool and design-specific algorithm discovery for the open-source tool.
(a) Synthesis script tuning
Design
Baseline
Reduction ↑
WNS
TNS
Area
WNS
TNS
Area
(ns)
(ns)
( μ m 2 )
FIFO
−0.45
−1801.81
34987
7.0%
2.5%
0.1%
SHA3
−0.74
−1494.83
33639
4.1%
12.9%
−0.2%
SPI
−0.24
−25.67
1881
6.9%
14.8%
0.5%
Table 2. Results of (a) commercial DC script tuning and (b) open-source synthesis algorithm discovery. Baselines are Dr. RTL’s best RTL under compile_ultra and agent-tuned Yosys+ABC, respectively. Positive percentages indicate improvement. Mean is arithmetic.
Figure 8. Future vision of self-improving cross-layer agentic DSE. Optimization spans architecture, RTL, and EDA algorithms, with verification defining the allowable freedom at each level. Tool feedback and reusable knowledge support continual improvement across design stages.
Recent advances in large language models (LLMs) have sparked growing interest in automatic RTL optimization for better performance, power, and area (PPA). However, existing methods are still far from realistic RTL optimization. Their evaluation settings are often unrealistic: they are tested on manually degraded, small-scale RTL designs and rely on weak open-source tools. Their optimization methods are also limited, relying on coarse design-level feedback and simple pre-defined rewriting rules. To address these limitations, we present Dr. RTL, an agentic framework for RTL timing optimization in a realistic evaluation environment, with continual self-improvement through reusable optimization skills. We establish a realistic evaluation setting with more challenging RTL designs and an industrial EDA workflow. Within this setting, Dr. RTL performs closed-loop optimization through a multi-agent framework for critical-path analysis, parallel RTL rewriting, and tool-based evaluation. We further introduce group-relative skill learning, which compares parallel RTL rewrites and distills the optimization experience into an interpretable skill library. Currently, this library contains 47 pattern--strategy entries for cross-design reuse to improve PPA and accelerate convergence, and it can continue evolving over time. Evaluated on 20 real-world RTL designs, Dr. RTL achieves average WNS/TNS improvements of 21%/17% with a 6% area reduction over the industry-leading commercial synthesis tool.
Wenji Fang, Yao Lu, Shang Liu +5
Hong Kong University of Science and Technology (HKUST)
Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis reports and reasons over the current circuit state, retrieved tool knowledge, and historical optimization experience to issue targeted commands. SynAct focuses on improving timing, particularly worst negative slack (WNS), while maintaining balanced area and power trade-offs. Experiments on a commercial synthesis tool across 14 designs show that SynAct reduces average WNS to 27% of that from bootstrap synthesis.
Fangzhou Liu, Peiyi Han, Jiawei Liu +5
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR.
This paper introduces the first self-evolving logic synthesis framework, which leverages Large Language Model (LLM) agents to autonomously improve the source code of ABC, the widely adopted logic synthesis system. Our framework operates on the entire integrated ABC codebase, and the output repository preserves its single-binary execution model and command interface. In the initial evolution cycle, we bootstrap the system using existing prior open-source synthesis components, covering flow tuning, logic minimization, and technology mapping, but without manually injecting new heuristics. On top of this foundation, a team of LLM-based agents iteratively rewrites and evolves specific sub-components of ABC following our programming guidance prompts under a unified correctness and QoR-driven evaluation loop. Each evolution cycle proposes code modifications, compiles the integrated binary, validates correctness, and evaluates quality-of-results (QoR) on multi-suite benchmarks including ISCAS85/89/99, VTR, EPFL, and IWLS2005. Through continuous feedback, the system discovers optimizations beyond human-designed heuristics, effectively learning new synthesis strategies that enhance QoR. We detail the architecture of this self-improving system, its integration with ABC, and results demonstrating that the framework can autonomously and progressively improve EDA tool at full million-line scale.
Cunxi Yu, Haoxing Ren
NVIDIA Research University of Maryland USA · NVIDIA Research USA