通过验证器反馈进化技能，让硬件大模型更高效解决复杂电路设计问题。
Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents
- 将自然语言技能视为可演化的策略，利用失败与成功轨迹生成诊断信息。
- 在不微调模型的前提下，任务通过率显著提升，突破多个此前无法解决的问题。
- 适用于需要验证的硬件设计任务，也可扩展到其他可验证工程领域。
复杂Verilog设计问题（CVDP）对硬件大模型代理构成挑战，因其需在大型代码库快照中定位与验证相关的RTL、测试平台、包含路径和构建依赖，进行精确编辑并从稀疏的隐藏验证失败中恢复。我们提出Trace2Skill，一种无需RTL特化模型微调的测试时扩展框架。该框架将代理的自然语言技能视为可演化的策略，挖掘重复的执行轨迹以识别成功与失败模式，转化为密集诊断与验证规则，并通过验证器、变异器与选择器循环生成任务特定技能，指导后续搜索、编辑、验证与恢复。由于最终通过/失败标签往往对严重错误过于粗略，Trace2Skill还支持有界运行时间的密集验证反馈，返回净化后的功能观测结果，同时保持隐藏测试平台和参考解不可见。该反馈将技能文本、验证证据与下游行为关联，驱动技能演化与代理执行。在击败初始CVDP代理的难题上，包括一些也超越前沿编码代理的任务，Trace2Skill结合密集验证反馈显著提升任务通过率，并在先前无法解决的任务上实现突破性通过，且无需高质量微调数据、专用RTL训练或模型权重更新。该框架亦提供通用的测试时扩展策略，可推广至其他可验证的EDA任务。
原文摘要 · Abstract (English)
Complex Verilog Design Problems (CVDP) challenge hardware LLM agents because solving them requires localizing verifier-relevant RTL, testbenches, include paths, and build dependencies inside large repository snapshots, making precise edits, and recovering from sparse hidden-verifier failures. We present Trace2Skill, a test-time scaling framework that improves a hardware agent without RTL-specialized model fine-tuning. Rather than training a new model or only sampling more candidate solutions, Trace2Skill treats the agent's natural-language skill as an evolvable policy. It mines repeated rollout traces for success and failure modes, converts them into dense diagnostics and oracle lessons, and uses an oracle, mutator, and selector loop to produce task-specific skills that guide later search, editing, validation, and recovery. Because final pass/fail labels are often too coarse for hard failures, Trace2Skill also supports bounded runtime dense verifier feedback that returns sanitized functional observations while keeping hidden harnesses and reference solutions inaccessible to the agent. This feedback helps guide skill evolution and agent execution by connecting skill text, verifier evidence, and downstream behavior. Across hard CVDP tasks that defeat the seed CVDP agent, including tasks that also defeat frontier coding agents, Trace2Skill with dense verifier feedback substantially improves task pass rates and produces breakthrough passes on previously unsolved tasks, without requiring high-quality fine-tuning data, specialized RTL model training, or model weight updates. The same framework provides a general test-time scaling strategy that can extend beyond digital design to other verifiable EDA tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。