RF-Agent is presented, which addresses the gap in domain-specific RF reasoning through textbook-driven knowledge distillation through a multi-agent Question-Thinking-Solution-Answer pipeline and provides a reusable foundation for future work on LLM-aided RF circuit design.
Abstract
Large language models (LLMs) have driven rapid progress in electronic design automation (EDA), yet their application to radio-frequency (RF) circuit design remains limited by the scarcity of domain-specific datasets and standardized benchmarks. We present RF-Agent, which addresses this gap through textbook-driven knowledge distillation. A multi-agent Question-Thinking-Solution-Answer (QTSA) pipeline converts a subsection-level corpus from seven canonical RF textbooks into the first-of-its-kind RF-domain reasoning dataset (over 11,000 samples) with a dedicated multiple-choice benchmark. On this benchmark we study two adaptation strategies: supervised fine-tuning (SFT) and three retrieval-augmented generation (RAG) configurations (semantic, keyword, hybrid). Across multiple LLM families, domain-specific SFT significantly improves RF reasoning, especially for small and medium-sized models; among RAG configurations, semantic retrieval performs best, indicating embedding-based context alignment suits RF reasoning better than naive fusion. The dataset and benchmark provide a reusable foundation for future work on LLM-aided RF circuit design.
This work reveals that retrieval from a structured agent repository provides a cost-efficient, accurate, and controllable alternative to dynamic agent generation, responding to the strict demands of industrial applications.
Vitalii Belov, Artyom Sosedka, Andrey Sakhovskiy et al.· Annual International ACM SIG...· 0 citations
A novel RAIE taxonomy along four scaling dimensions is proposed, which optimizes the entire thought process through search algorithms and self-verification, and introduces a task-oriented guideline for choosing the best TTS strategy.
Jiayu An, Zheng Chen, Yongcheng Jing et al.· 0 citations
A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings, and presents AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications.
Hao Jiang, Gangtao Xin, Ying Huang et al.· 0 citations
PoTRE (Poly-Topological Reasoning Ensembles), a heterogeneous framework that decouples inference into four agents that achieves improved reasoning performance using similar or fewer inference tokens compared to heavily scaled homogeneous baselines is introduced.
Constructing simulation scenarios manually is time-consuming and often depends on platform-specific modeling experience. Existing large-language-model (LLM) methods are promising for interpreting operational documents, but they still struggle with long-document parsing, incomplete platform interfaces, auditable task execution, and cross-lingual equipment-name normalization. This paper proposes a dual-channel LLM-agent framework for intelligent generation of simulation scenarios. The method standardizes Word-based scenario inputs, extracts scenario elements into a schema-constrained JSON intermediate representation, and decomposes the generation process into planning and execution. A DLL/Lua dual-channel Plan Agent assigns basic object and scenario-property operations to a C# object model, while allocating fine-grained unit, mission, and environment operations to Lua-based scripting interfaces. An Exec Agent further integrates two-stage hot-pluggable tool loading, side-effect-aware read/write-separated scheduling, and a Smart-Matcher module that combines BM25 retrieval, multilingual vector retrieval, reciprocal rank fusion, and low-confidence LLM reranking. Experiments on representative red-blue simulation scenarios show an average end-to-end generation time of 168 s, a first-round planning success rate of 92.0%, a post-Replan success rate of 100.0%, and Top-1/Top-5 equipment matching performance of 95.6% and 98.4%, respectively.
Lei Wang, Zhiqiang Fan, Yikang Song et al.· 2026 IEEE 27th China Confere...· 0 citations
Introduction: Large Language Models (LLMs) have catalyzed rapid adoption in educational technology, with 37% of secondary teachers globally using generative AI tools. However, deployment predominantly occurs through monolithic architectures where single models handle diverse functions without specialization for adaptive learning constraints. This work presents the design and implementation of a mobile adaptive learning platform for primary mathematics education, featuring a specialized multi-agent LLM architecture.
Method: The proposed system implements four functionally distinct agents—Pattern Analyzer for cognitive profiling, Curriculum Architect for personalized sequencing, Exercise Selector for dynamic content generation, and Feedback Provider for constructivist support—coordinated by a central orchestrator following the Mediator design pattern. Each agent is independently optimized with specialized prompts and intelligent selection between GPT-4o and GPT-4o-mini, incorporating hybrid routing between template responses and dynamic LLM generation for feedback.
Results: Development testing over three months consumed approximately 1 million tokens across 192 API requests, incurring $3.72 total cost and projecting per-student costs of $0.25-0.30, with the hybrid feedback strategy achieving approximately 85% cost reduction. A pilot test with a single student demonstrated technical feasibility through successful cognitive profile generation, personalized curriculum sequencing, and system integration.
Conclusions: The multi-agent approach shows that specialized architectures enable targeted optimization unavailable in monolithic systems, establishing an engineering framework for adaptive learning platforms, while pedagogical effectiveness still requires future experimental validation with learners in controlled studies.
Gustavo De-Avila-Herrera, E. F. Parra-González, José Eder Guzmán-Mendoza et al.· Publicaciones· 0 citations
