# HARGO: Heterogeneity-Aware Reward-Guided Optimization for RL Post-Training of LLMs on HPC Tasks

arXiv: https://arxiv.org/abs/2607.28301 · HTML: https://mlsanity.com/paper/2607.28301/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [The Landscape and Challenges of HPC Research and LLMs](https://mlsanity.com/paper/2402.02018/) (2024)
- [Performance-Aligned LLMs for Generating Fast Code](https://mlsanity.com/paper/2404.18864/) (2024)
- [OMPGPT: A Generative Pre-trained Transformer Model for OpenMP](https://mlsanity.com/paper/2401.16445/) (2024)
- [Scope is all you need: Transforming LLMs for HPC Code](https://mlsanity.com/paper/2308.09440/) (2023)
- [MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks](https://mlsanity.com/paper/2312.13322/) (2023)
- [HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages](https://mlsanity.com/paper/2412.15178/) (2024)
- [LLM & HPC:Benchmarking DeepSeek's Performance in High-Performance Computing Tasks](https://mlsanity.com/paper/2504.03665/) (2025)
- [OMPar: Automatic Parallelization with AI-Driven Source-to-Source Compilation](https://mlsanity.com/paper/2409.14771/) (2024)
- [LLM as HPC Expert: Extending RAG Architecture for HPC Data](https://mlsanity.com/paper/2501.14733/) (2024)
- [Exploring the Role of LLMs in HPC Programming: A Survey](https://mlsanity.com/paper/2608.26110/) (2026)

## Abstract (arXiv)

Supervised fine-tuning (SFT) can equip large language models (LLMs) with domain knowledge for high-performance computing (HPC) tasks such as data race detection and benchmark question answering. However, knowledge alone does not guarantee task-appropriate behavior: the same SFT model that correctly classifies 88.65% of C/C++ data race samples produces verbose, imprecise answers to factual queries, with 65.9% of MLPerf responses exceeding 40 characters. Reinforcement learning (RL) post-training addresses this gap by optimizing for task-specific rewards rather than token-level imitation. Yet HPC tasks exhibit extreme heterogeneity, with binary classification, factual QA, and semantic generation differing by 58x in answer length, spanning three distinct reward distributions, and showing widely varying SFT accuracy. This makes uniform-weight RL methods such as GRPO suboptimal. We propose HARGO, Heterogeneity-Aware Reward-Guided Optimization, which introduces per-response importance weighting via confidence-modulated advantage: computing a discrimination signal from group-level reward contrast and a confidence signal from reference model log-probabilities, then modulating the advantage before computing per-response weights, without requiring task-type labels. Across four HPC tasks and nine methods, HARGO achieves the best performance on all three primary metrics: WinRate 54.62%, Data Race F1 91.30%, and PLP Similarity 0.8558. Ablation confirms complementary contributions from both signals. HARGO establishes the best overall alignment quality among compared methods for heterogeneous HPC tasks.