# AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework

arXiv: https://arxiv.org/abs/2510.11759 · HTML: https://mlsanity.com/paper/2510.11759/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 13 of 13)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [AIOS: LLM Agent Operating System](https://mlsanity.com/paper/2403.16971/) (2024)
- [Large Language Models for Compiler Optimization](https://mlsanity.com/paper/2309.07062/) (2023)
- [CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research](https://mlsanity.com/paper/2109.08267/) (2021)
- [Meta Large Language Model Compiler: Foundation Models of Compiler Optimization](https://mlsanity.com/paper/2407.02524/) (2024)
- [AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.00671/) (2020)
- [Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning](https://mlsanity.com/paper/2506.15701/) (2025)
- [Compiler Auto-tuning through Multiple Phase Learning](https://mlsanity.com/paper/2304.14908/) (2023)

## Built on by (most cited first, 4 of 4)

- [AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems](https://mlsanity.com/paper/2601.09393/) (2026)
- [AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning](https://mlsanity.com/paper/2606.20373/) (2026)
- [FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications](https://mlsanity.com/paper/2607.18171/) (2026)
- [ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization](https://mlsanity.com/paper/2602.00087/) (2026)

## Abstract (arXiv)

Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software optimization, automating compiler optimization remains challenging due to: (1) semantic misalignment between abstract program representations and concrete optimization passes, (2) inefficient interaction mechanisms between agents and compiler environments, and (3) reward sparsity from the extensive decision-making process within large optimization spaces. This paper introduces AwareCompiler, an agentic framework for compiler optimization that addresses these challenges through three key innovations: structured knowledge integration and dataset construction, knowledge-driven adaptive pass generation, and data-driven hybrid training pipeline. Experimental results on standard benchmarks demonstrate that AwareCompiler significantly outperforms existing baselines in both performance and efficiency, highlighting the effectiveness of our synergistic knowledge-data-driven approach. Our code is publicly available at https://github.com/LHY-24/AwareCompiler.