# ArchAgent v2: A Case Study with the Data Prefetching Championship

arXiv: https://arxiv.org/abs/2608.09874 · HTML: https://mlsanity.com/paper/2608.09874/

## Key facts

- Cited by 1 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 16 of its 34 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Barbarians at the Gate: How AI is Upending Systems Research](https://mlsanity.com/paper/2510.06189/) (2025)
- [ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence](https://mlsanity.com/paper/2605.26340/) (2026)
- [Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning](https://mlsanity.com/paper/2109.12021/) (2021)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [The Championship Simulator: Architectural Simulation for Education and Competition](https://mlsanity.com/paper/2210.14324/) (2022)
- [Improving Coherence and Persistence in Agentic AI for System Optimization](https://mlsanity.com/paper/2603.21321/) (2026)
- [ArchAgent: Agentic AI-driven Computer Architecture Discovery](https://mlsanity.com/paper/2602.22425/) (2026)
- [Computer Architecture's AlphaZero Moment: Automated Discovery in an Encircled World](https://mlsanity.com/paper/2604.03312/) (2026)
- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [CHIA: An open-source framework for principled, agentic AI-driven hardware/software co-design research](https://mlsanity.com/paper/2606.27350/) (2026)
- [Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization](https://mlsanity.com/paper/2604.25083/) (2026)
- [Coordinated Reinforcement Learning Prefetching Architecture for Multicore Systems](https://mlsanity.com/paper/2509.10719/) (2025)

## Built on by (most cited first, 1 of 1)

- [DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck](https://mlsanity.com/paper/2610.17184/) (2026)

## Abstract (arXiv)

Agentic artificial intelligence has shown great promise in automating algorithm design, but scaling similar techniques to computer microarchitecture discovery remains challenging due to vast search spaces, strict hardware budgets, and long simulation times. In this work, we present ArchAgent v2, a framework which scales automated microarchitecture search to multi-level data prefetching. While the original ArchAgent successfully discovered single-level cache replacement policies in competition settings, it does not scale to multi-level prefetching where the design space and degrees of freedom are larger. To overcome this, we introduce two new additions to ArchAgent: a cascaded evolutionary search that subdivides the design space by sequentially evolving and freezing prefetchers at individual cache levels, and a hardware-realizability feedback loop that embeds real-time size-estimation directly into the evolution process. Evaluated under identical rules of the 4th Data Prefetching Championship (DPC4), ArchAgent v2 automatically designs a three-level prefetcher that outperforms the winning hand-designed solution, further demonstrating automated agentic discovery as a useful tool for computer architects. Our discovered policy achieves a 3.8% geometric mean IPC speedup over the baseline overall and a 0.3% improvement over the prior champion, BertiGO. On low-bandwidth single-core configurations, our policy yields a 4.6% performance speedup compared to only 2.6% for BertiGO. However, multi-core evolution still remains a significant challenge due to simulation latency impeding evolution speed. Finally, our profiling of an ArchAgent evolution of over 12,000 candidate designs provides key insights into how automated evolutionary agents explore and synthesize complex microarchitectural logic.