DS2Agent: Holistic Device Agents for Accelerated Embedded Board-Level Design
Organizations: Shandong University · GDUFE-UCM Joint Institute, Guangdong University of Finance & Economic
Abstract
Embedded board-level development demands extensive expertise, from component selection and device characteristics to interface configuration, driver writing, and system composition. Recently, LLM-based agents have shown strong capabilities, raising the prospect of automating board-level design tasks. However, existing agents either target chip-level design or treat datasheets as static text, offering little guidance on whether a specific component should---or even could---be used for a given board-level design. Moreover, without touching real hardware, they hallucinate incorrect details. To fill this gap, we present {\setlength{\fboxsep}{1pt}blue{white}{DS2Agent}}, an open-source framework that constructs interactive agents from device datasheets. Each agent comprises three models: a knowledge model supporting retrieval and question answering; a digital-twin model capturing the physical functionality of the device; and an interface model supporting driver development and system integration. To suppress hallucinations, we also allow optional connections to real devices, so that the agent can calibrate its internalized knowledge against the device. We evaluate DS2Agent on ten devices spanning seven functional categories. Compared with the baseline, the DS2Agent-augmented agent improves the question-answering score from 87 to 97 out of 100 while using 44.8% fewer tokens. For driver generation, it reduces average token usage per device by 72.9%. For system integration, it reduces total token usage across three FreeRTOS applications by 29.7%.
Figures & tables
| Work | Board Level | Digital Twin | Hardware Calibration | MCP Interface | Design Exploration |
| Arduino MCP [ 4 ] | ✓ | ✗ | ✗ | ✓ | ✓ |
| Embedded MCP [ 5 ] | ✓ | ✗ | ✗ | ✓ | ✓ |
| Labgrid [ 6 ] | ✓ | ✗ | ✗ | ✗ | ✓ |
| Renode [ 7 ] | ✓ | ✓ | ✗ | ✗ | ✓ |
| Eclipse Ditto [ 8 ] | ✗ | ✓ | ✗ | ✗ | ✗ |
| OpenCalib [ 9 ] | ✗ | ✗ | ✓ | ✗ | ✓ |
| Question Category | Questions | Augmented Agent Score | Baseline Agent Score |
| Communication | 20 | 20 | 19 |
| Power Consumption and Supply | 20 | 20 | 18 |
| Functionality | 20 | 20 | 20 |
| Timing | 20 | 20 | 16 |
| Electrical Characteristics and Interference | 10 | 8 | 7 |
| Reliability and Environmental Conditions | 10 | 9 | 7 |
| Device | Augmented agent | Baseline agent | ||
| Token usage | Time (s) | Token usage | Time (s) | |
| SHT31 | 2,258,912 | 20 | 6,633,968 | 800 |
| ADXL345 | 2,714,985 | 31 | 9,194,883 | 648 |
| QMC5883L | 2,801,481 | 30 | 9,917,133 | 818 |
| HX711 | 2,424,998 | 25 | 12,362,224 | 968 |
| INA219 | 2,975,487 | 22 | 15,647,209 | 489 |
LLM Agents
Large language model agents use language models to plan, use tools, and act across multi-step tasks and environments.
See all 774 papers