mlsanityData to 7 Oct 2026

Evidence-Driven LLM Agent for C-to-Synthesizable-C Conversion and Verification

arXiv 2606.28409 ↗First posted 25 Jun 2026cs.AR cs.AIcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Software-compilable C programs routinely fail to complete the four-stage pipeline of a high-level synthesis (HLS) toolchain -- compilation, C simulation (CSim), synthesis, and C/RTL co-simulation (CoSim) -- because HLS accepts only a synthesizable subset of C (HLS-C). Yet most existing large language model (LLM) systems built for HLS code repair only cover the early pipeline stages and feed raw tool logs directly to the model, yielding brittle and hard-to-reproduce fixes. We formulate C-to-HLS-C conversion as a closed-loop generation-verification-diagnosis-repair problem on an HLS tool (Xilinx Vitis), contributing three components: an end-to-end workflow of cooperating agents closed by the four-stage verifier under strict evidence isolation; a Progressive Mismatch Localization Chain (PMLC) that localizes CSim/CoSim mismatches through log normalization, AST backward slicing, and dual-trace instrumentation; and a typed-query, two-stage evidence RAG backed by a self-evolving, family-routed repair-card pool. Experimental results show that the proposed workflow substantially outperforms all comparable state-of-the-art models.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 32 of its 46 references that are in the map. First posted on arXiv 25 Jun 2026.

Builds on

32 of 46 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation31 Oct
  2. 2025Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective17 Mar
  3. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repair25 Mar
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug

Other references · 28

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  5. 2023StarCoder: may the source be with you!cited by 790
  6. 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 246
  7. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 197
  8. 2023RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Modelcited by 143
  9. 2022Practical Program Repair in the Era of Large Pre-trained Language Modelscited by 133
  10. 2023RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solutioncited by 69
  11. 2022Repair Is Nearly Generation: Multilingual Program Repair with LLMscited by 68
  12. 2020AutoDSE: Enabling Software Programmers to Design Efficient FPGA Acceleratorscited by 25
16 more
  1. 2024HLSPilot: LLM-based High-Level Synthesiscited by 24
  2. 2024Automated C/C++ Program Repair for High-Level Synthesis via Large Language Modelscited by 18
  3. 2024C2HLSC: Leveraging Large Language Models to Bridge the Software-to-Hardware Design Gapcited by 16
  4. 2025AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Taskscited by 16
  5. 2024Ask-EDA: A Design Assistant Empowered by LLM, Hybrid RAG and Abbreviation De-hallucinationcited by 14
  6. 2025HLS-Eval: A Benchmark and Framework for Evaluating LLMs on High-Level Synthesis Design Taskscited by 10
  7. 2025SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generationcited by 9
  8. 2025LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuningcited by 8
  9. 2025ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesiscited by 6
  10. 2024SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generationcited by 5
  11. 2025TimelyHLS: LLM-Based Timing-Aware and Architecture-Specific FPGA HLS Optimizationcited by 5
  12. 2024ORAssistant: A Custom RAG-based Conversational Assistant for OpenROADcited by 4
  13. 2025HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutionscited by 4
  14. 2025HLStrans: Dataset for C-to-HLS Hardware Code Synthesiscited by 3
  15. 2025CorrectHDL: Agentic HDL Design with LLMs Leveraging High-Level Synthesis as Referencecited by 3
  16. 2025DeepV: A Model-Agnostic Retrieval-Augmented Framework for Verilog Code Generation with a High-Quality Knowledge Basecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Shift-Left High-Level Synthesis Verification via Knowledge-Augmented LLM Agent ↗
  2. 2026Open-Source LLM-Driven Formal Verification: A Multi-Agent Pipeline for RTL Repair
  3. 2025HLSTester: Efficient Testing of Behavioral Discrepancies with LLMs for High-Level Synthesis ↗
  4. 2026Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code
  5. 2025Workflows vs Agents for Code Translation
  6. 2026HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation
  7. 2026AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance
  8. 2026P3: Joint Program-and-Proof Planning for Verified Code Generation