# Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve

arXiv: https://arxiv.org/abs/2601.21096 · HTML: https://mlsanity.com/paper/2601.21096/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization](https://mlsanity.com/paper/2509.14279/) (2025)
- [Barbarians at the Gate: How AI is Upending Systems Research](https://mlsanity.com/paper/2510.06189/) (2025)
- [Large Language Models for Compiler Optimization](https://mlsanity.com/paper/2309.07062/) (2023)
- [Structured Evolution with Compact Architectures for Scalable Policy Optimization](https://mlsanity.com/paper/1804.02395/) (2018)
- [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)
- [Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients](https://mlsanity.com/paper/2010.01709/) (2020)
- [HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization](https://mlsanity.com/paper/2506.07972/) (2025)
- [Allo: A Programming Model for Composable Accelerator Design](https://mlsanity.com/paper/2404.04815/) (2024)
- [Autonomous Code Evolution Meets NP-Completeness](https://mlsanity.com/paper/2509.07367/) (2025)
- [AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning](https://mlsanity.com/paper/1901.04615/) (2019)
- [Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training](https://mlsanity.com/paper/2302.08005/) (2023)
- [PartIR: Composing SPMD Partitioning Strategies for Machine Learning](https://mlsanity.com/paper/2401.11202/) (2024)
- [MLGOPerf: An ML Guided Inliner to Optimize Performance](https://mlsanity.com/paper/2207.08389/) (2022)
- [Agentic Operator Generation for ML ASICs](https://mlsanity.com/paper/2512.10977/) (2025)
- [Tawa: Automatic Warp Specialization for Modern GPUs with Asynchronous References](https://mlsanity.com/paper/2510.14719/) (2025)
- [Dato: A Task-Based Programming Model for Dataflow Accelerators](https://mlsanity.com/paper/2509.06794/) (2025)
- [Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs](https://mlsanity.com/paper/2512.18134/) (2025)
- [e-boost: Boosted E-Graph Extraction with Adaptive Heuristics and Exact Solving](https://mlsanity.com/paper/2508.13020/) (2025)

## Built on by (most cited first, 5 of 5)

- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation](https://mlsanity.com/paper/2602.07670/) (2026)
- [From I/O to Code with Discovery Agent](https://mlsanity.com/paper/2605.15334/) (2026)
- [AI-PROPELLER: Warehouse-Scale Interprocedural Code Layout Optimization with AlphaEvolve](https://mlsanity.com/paper/2606.00131/) (2026)
- [LLM-Guided Strategy Synthesis for Scalable Equality Saturation](https://mlsanity.com/paper/2604.17364/) (2026)

## Abstract (arXiv)

Modern compilers rely on hand-crafted heuristics to guide optimization passes. These human-designed rules often struggle to adapt to the complexity of modern software and hardware and lead to high maintenance burden. To address this challenge, we present Magellan, an agentic framework that evolves the compiler pass itself by synthesizing executable C++ decision logic. Magellan couples an LLM coding agent with evolutionary search and autotuning in a closed loop of generation, evaluation on user-provided macro-benchmarks, and refinement, producing compact heuristics that integrate directly into existing compilers. Across several production optimization tasks, Magellan discovers policies that match or surpass expert baselines. In LLVM function inlining, Magellan synthesizes new heuristics that outperform decades of manual engineering for both binary-size reduction and end-to-end performance. In register allocation, it learns a concise priority rule for live-range processing that matches intricate human-designed policies on a large-scale workload. We also report preliminary results on XLA problems, demonstrating portability beyond LLVM with reduced engineering effort.