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

• URL: http://arxiv.org/abs/2606.28409v1
• Date: Thu, 25 Jun 2026 02:55:02 GMT
• Title: Evidence-Driven LLM Agent for C-to-Synthesizable-C Conversion and Verification
• Abstract summary: C programs fail to complete the four-stage pipeline of a high-level synthesis (HLS) toolchain.<n>We formulate C-to-HLS-C conversion as a closed-loop generation-verification-diagnosis-repair problem on an HLS tool.
• Score: 3.285367305212235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Foundational Constraint Solving for Expressive Refinement Typing [0.9624643581968987]
  We present FLEX, a Constrained Horn Clause (CHC) solver implemented in LEAN.<n>We show how FLEX reduces the trusted base to the kernel alone, and allows using LEAN's entire proof ecosystem to verify low-level systems code.
  arXiv  Detail & Related papers  (2026-07-14T00:15:23Z)
• From I/O to Code with Discovery Agent [103.88427301265669]
  We propose DIO-Agent, a discovery agent for IO2Code.<n>Our method frames IO2Code as an evolutionary search over discrete program space.<n>Extensive experiments show that DIO-Agent consistently outperforms both traditional program-by-example method and SOTA evolution-agent baselines.
  arXiv  Detail & Related papers  (2026-05-14T18:57:32Z)
• ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation [55.947962672433675]
  ChipMATE is the first self-trained multi-agent framework for RTL generation.<n>Inspired by industrial practice, ChipMATE pairs a Verilog agent with a Python reference-model agent that mutually verify each other's outputs.<n>ChipMATE achieves 75.0% and 80.1% pass@1 on VerilogEval V2 with 4B and 9B base models.
  arXiv  Detail & Related papers  (2026-05-13T01:04:21Z)
• Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards [76.49428173793386]
  LLMs must invoke multiple dependent APIs in the correct order while propagating intermediate outputs.<n>Training models to handle such faces two obstacles: existing environments focus on simple per-turn function calls with simulated data, and binary rewards.<n>We present a framework addressing both challenges. First, we construct a reinforcement learning environment backed by a large-scale cache of real API responses, enabling a data synthesis pipeline that samples valid multi-step orchestration traces.<n>Second, we propose a graduated reward design that decomposes correctness into atomic validity and orchestration.
  arXiv  Detail & Related papers  (2026-03-25T18:31:39Z)
• Toward Automated Virtual Electronic Control Unit (ECU) Twins for Shift-Left Automotive Software Testing [0.0]
  Automotive software increasingly outpaces hardware availability, forcing late integration and expensive hardware-in-the-loop (HiL) bottlenecks.<n>InnoRegioChallenge investigated whether a virtual test and integration environment can reproduce electronic control unit (ECU) behavior early enough to run real software binaries before physical hardware exists.<n>We report a prototype that generates instruction-accurate processor models in SystemC/TLM2.0 using an agentic, feedback-driven workflow.
  arXiv  Detail & Related papers  (2026-02-20T11:03:46Z)
• Focus Session: LLM4PQC -- An Agentic Framework for Accurate and Efficient Synthesis of PQC Cores [12.18204758079849]
  The design of post-quantum cryptography (PQC) hardware is a complex and hierarchical process.<n>A primary bottleneck is the conversion of PQC reference codes from C to high-level synthesis (HLS) specifications.<n>Here, we propose LLM4PQC, an agentic framework that synthesizes high-level PQC specifications and reference C codes into synthesizable C code.
  arXiv  Detail & Related papers  (2026-02-10T15:53:37Z)
• TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents [70.68963723787424]
  TermiGen is an end-to-end pipeline for synthesizing verifiable environments and resilient expert trajectories.<n>Our TermiGen-Qwen2.5-Coder-32B achieves a 31.3% pass rate on TerminalBench.
  arXiv  Detail & Related papers  (2026-02-06T23:56:50Z)
• Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation [4.723302382132762]
  silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations, and (iii) semantic drift as intent is reinterpreted across agent handoffs.<n>We propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs.
  arXiv  Detail & Related papers  (2026-01-27T16:10:23Z)
• Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning [65.20602712957725]
  Caco is a novel framework that automates the synthesis of high-quality, verifiable, and diverse instruction-CoT reasoning data.<n>Our work establishes a paradigm for building self-sustaining, trustworthy reasoning systems without human intervention.
  arXiv  Detail & Related papers  (2025-10-05T07:59:24Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• HLSTester: Efficient Testing of Behavioral Discrepancies with LLMs for High-Level Synthesis [4.544714097232974]
  Existing methods for testing behavioral discrepancies in high-level synthesis (HLS) are still immature.<n>We propose HLSTester, a large language model (LLM) aided testing framework that efficiently detects behavioral discrepancies in HLS.<n>To mitigate hallucinations in LLMs, the testbenches for original C/C++ programs are leveraged to guide LLMs in generating HLS-compatible testbenches.
  arXiv  Detail & Related papers  (2025-04-20T14:45:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.