Workflows vs Agents for Code Translation

• URL: http://arxiv.org/abs/2512.14762v1
• Date: Mon, 15 Dec 2025 20:35:11 GMT
• Title: Workflows vs Agents for Code Translation
• Authors: Henry Gray, Tom Yotam, Octavian Udrea,
• Abstract summary: Large language models (LLMs) offer a path to automation, their limited training on HDL code makes end-to-end transpilation brittle and prone to syntax errors.<n>We compare two methods for syntax repair in a LLM-to-HDL pipeline: a structured, expert-designed flow that follows a fixed sequence of operations, and a more autonomous agentic approach that uses the Model Context Protocol (MCP)<n>Across three model scales, the agentic approach is more effective at resolving initial syntax errors, a greater number of candidates to proceed through the pipeline.
• Score: 2.102846336724103
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Translating algorithms from high-level languages like MATLAB to hardware description languages (HDLs) is a resource-intensive but necessary step for deployment on FPGAs and ASICs. While large language models (LLMs) offer a path to automation, their limited training on HDL code makes end-to-end transpilation brittle and prone to syntax errors. We compare two LLM-driven methods for syntax repair in a MATLAB-to-HDL pipeline: a structured, expert-designed flow that follows a fixed sequence of operations, and a more autonomous agentic approach that uses the Model Context Protocol (MCP) \cite{anthropic2024mcp} to dynamically select its own tools. We study 42 MATLAB signal-processing functions and isolate the syntax-repair stage. Across three model scales, the agentic approach is more effective at resolving initial syntax errors, unblocking a greater number of candidates to proceed through the pipeline. This upstream improvement yields measurable downstream improvements, most notably on mid-sized models, where it increases the simulation reach rate by over 20 percentage points. We hypothesize the gains come from short prompts, aggressive context management, and conditional tool use. Conditional retrieval helps at 8B and 30B; at 235B final-success gains are small and a naive RAG variant attains the highest final success. Our findings suggest that these agentic frameworks, when properly designed, are most effective at compensating for the capacity limits of small and mid-sized models.

Related papers

• AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent [80.83250816918861]
  Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in natural language reasoning with long chain-of-thought.<n>However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations.<n>We present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision.
  arXiv  Detail & Related papers  (2025-12-23T19:57:49Z)
• ML-Tool-Bench: Tool-Augmented Planning for ML Tasks [23.54937738755734]
  We introduce a benchmark for evaluating tool-augmented machine learning agents.<n>Our benchmark goes beyond traditional tool-use evaluation by incorporating an in-memory named object management.<n>Our approach improves over ReAct by 16.52 percentile positions, taking the median across all Kaggle challenges.
  arXiv  Detail & Related papers  (2025-11-29T23:59:40Z)
• Continuous Autoregressive Language Models [56.49239051750678]
  We introduce Continuous Autoregressive Language Models (CALM)<n>CALM uses a high-fidelity autoencoder to compress a chunk of K tokens into a single continuous vector.<n>We develop a comprehensive likelihood-free framework that enables robust training, evaluation, and controllable sampling.
  arXiv  Detail & Related papers  (2025-10-31T17:58:11Z)
• Reasoning Distillation and Structural Alignment for Improved Code Generation [0.6933020649563103]
  This work distills the reasoning capabilities of a large language model into a smaller, more efficient model that is faster and cheaper to deploy.<n>Our approach trains the model to emulate the reasoning and problem-solving abilities of the VLLM by learning to identify correct solution pathways.<n> Experimental results show that our fine-tuned model, developed through a cheap and simple to implement process, significantly outperforms our baseline model in terms of pass@1, average data flow, and average syntax match metrics.
  arXiv  Detail & Related papers  (2025-10-20T14:47:47Z)
• DELM: a Python toolkit for Data Extraction with Language Models [0.0]
  DELM (Data Extraction with Language Models) is an open-source Python toolkit designed for rapid experimental iteration of data extraction pipelines.<n>It minimizes boilerplate code and offers a modular framework with structured outputs, built-in validation, flexible data-loading and scoring strategies, and efficient batch processing.<n>It also includes robust support for working with LLM APIs, featuring retry logic, result caching, detailed cost tracking, and comprehensive configuration management.
  arXiv  Detail & Related papers  (2025-09-24T23:47:55Z)
• Reinforcement Learning for Machine Learning Engineering Agents [52.03168614623642]
  We show that agents backed by weaker models that improve via reinforcement learning can outperform agents backed by much larger, but static models.<n>We propose duration- aware gradient updates in a distributed asynchronous RL framework to amplify high-cost but high-reward actions.<n>We also propose environment instrumentation to offer partial credit, distinguishing almost-correct programs from those that fail early.
  arXiv  Detail & Related papers  (2025-09-01T18:04:10Z)
• Evaluating Large Language Models on Non-Code Software Engineering Tasks [4.381476817430934]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code understanding and generation.<n>We present the first comprehensive benchmark, which we name Software Engineering Language Understanding' (SELU)<n>SELU covers classification, regression, Named Entity Recognition (NER) and Masked Language Modeling (MLM) targets, with data drawn from diverse sources.
  arXiv  Detail & Related papers  (2025-06-12T15:52:32Z)
• The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs [45.08958917457921]
  Large language models (LLMs) still struggle across tasks outside of high-resource languages.<n>In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce.
  arXiv  Detail & Related papers  (2025-05-23T20:28:31Z)
• Distilling LLM Agent into Small Models with Retrieval and Code Tools [65.73762766854192]
  Agent Distillation is a framework for transferring reasoning capability and task-solving behavior from large language models into small language models.<n>Our results show that sLMs as small as 0.5B, 1.5B, 3B parameters can achieve performance competitive with next-tier larger 1.5B, 3B, 7B models.
  arXiv  Detail & Related papers  (2025-05-23T08:20:15Z)
• Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations [11.902947290205645]
  Large language models (LLMs) have advanced scientific computing, their use in CFD is automating.<n>We introduce a novel approach centered on domain-specific LLM adaptation.<n>A multi-agent framework orchestrates the process, autonomously verifying inputs, generating configurations, running simulations, and correcting errors.
  arXiv  Detail & Related papers  (2025-04-13T14:35:30Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)

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.