cd /news/ai-research/pcbschemagen-reward-guided-llm-code-… · home topics ai-research article
[ARTICLE · art-131325] src=github.com ↗ pub= topic=ai-research verified=true sentiment=· neutral

PCBSchemaGen: Reward-Guided LLM Code Synthesis for PCB Schematic Design

Researchers released PCBSchemaGen_v2, a repository containing two benchmark suites totaling 227 PCB schematic-synthesis tasks and a deterministic 5-layer structural verifier for scoring SKiDL designs against real-IC pin- and topology-level constraints without an LLM, API key, or cached results. The suites comprise PCBBench with 62 hand-authored tasks (17 Easy / 28 Medium / 17 Hard) spanning 41 commercial ICs and Open-Schematics-Eval with 165 tasks (40 Easy / 48 Medium / 77 Hard) spanning 439 commercial ICs, for 480 real ICs across 22 domains. The verifier runs five layers — L1 ERC, L1b Role, L2 Template, L3 Topology, and L4 Power — and is released under the MIT License, with the accompanying paper authored by Huanghaohe Zou, Peng Han, Emad Nazerian, Mafu Zhang, Zhicheng Guo, and Alex Q. Huang for 2026.

read3 min views1 publishedSep 16, 2026
PCBSchemaGen: Reward-Guided LLM Code Synthesis for PCB Schematic Design
Image: Michielbdejong (auto-discovered)

This repository provides the two benchmark suites and the deterministic 5-layer verifier from the paper PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Board (PCB) Schematic Design with Structured Verification.

It lets anyone (i) load the 227 PCB schematic-synthesis tasks, and (ii) run the deterministic structural verifier that scores a candidate SKiDL design against real-IC pin- and topology-level constraints — no LLM, no API key, and no cached results required.

PCBSchemaGen_v2/
├── benchmarks/
│   ├── pcbbench/benchmark.tsv                   # 62 hand-authored tasks (Easy/Medium/Hard)
│   └── open_schematics/ose_165_task_specs.json  # 165 tasks from public schematics
├── framework/
│   ├── topo/                                    # the deterministic 5-layer verifier (self-contained)
│   └── task_config.yaml                         # per-task verification parameters
├── kg/kg_open_schematics.json                   # schema-induced KG for Open-Schematics-Eval
├── component.json / kg_component.json / kg.json # schema-induced KG for PCBBench
├── requirements.txt
└── LICENSE
Suite Tasks Difficulty split Real ICs Domains
PCBBench ( benchmarks/pcbbench/benchmark.tsv ) 62 17 Easy / 28 Medium / 17 Hard 41 commercial 22
Open-Schematics-Eval ( benchmarks/open_schematics/ose_165_task_specs.json ) 165 40 Easy / 48 Medium / 77 Hard 439 commercial 22
Total 227 57 / 76 / 94 480 22

Each PCBBench task row specifies: task id, difficulty level, circuit type, the natural-language task, input/output nodes, input/output voltages, and the required-component set.

The verifier scores a candidate schematic against structural constraints derived from real IC datasheets — fully deterministic, with no golden reference and no functional simulation:

  1. L1 ERC — electrical invariants (VDD/GND disjointness, power reachability, ground integrity)
  2. L1b Role — pin-role compatibility under the 32-role schema
  3. L2 Template — per-IC subcategory connection templates
  4. L3 Topology — subgraph isomorphism vs. canonical motifs (half-bridge, sync-buck, three-phase inverter, …)
  5. L4 Power — domain-specific power rules (Kelvin source, decoupling, isolation, gate-resistor)

See the paper appendix (verification details) for the full predicate set and reward ladder.

python3 -m pip install -r requirements.txt   # networkx, pyyaml

The verifier is self-contained in framework/topo/ (only depends on networkx). It exposes, among others:

from framework.topo import (
    KGStore, index_snapshot,
    check_system_topology, is_complex_task,
    validate_complex_task, get_validation_feedback_for_llm,
)

kg = KGStore(base_dir=".")

snapshot = index_snapshot(...)

report = validate_complex_task(...)

Per-task verification parameters (match mode, enabled checks, skipped rules) live in framework/task_config.yaml. Exact function signatures are documented in each module's docstring under framework/topo/ and in the paper appendix.

Released under the MIT License (see LICENSE). Open-Schematics-Eval tasks are derived from the public open-schematics dataset (MIT). Vendor datasheets referenced during KG construction are cited, not redistributed.

@inproceedings{pcbschemagen2026,
  title     = {PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Board (PCB)
               Schematic Design with Structured Verification},
  author    = {Zou, Huanghaohe and Han, Peng and Nazerian, Emad and
               Zhang, Mafu and Guo, Zhicheng and Huang, Alex Q.},
  year      = {2026},
}
── more in #ai-research 4 stories · sorted by recency
── more on @pcbschemagen 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/pcbschemagen-reward-…] indexed:0 read:3min 2026-09-16 ·