# Archer: Towards Agentic Review for Compiler Optimizations

arXiv: https://arxiv.org/abs/2607.01808 · HTML: https://mlsanity.com/paper/2607.01808/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 49 references that are in the map.
- First posted on arXiv 2 Jul 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, 14 of 14)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Are self-explanations from Large Language Models faithful?](https://mlsanity.com/paper/2401.07927/) (2024)
- [Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering](https://mlsanity.com/paper/2502.06193/) (2025)
- [CL-bench: A Benchmark for Context Learning](https://mlsanity.com/paper/2602.03587/) (2026)
- [CodeAgent: Autonomous Communicative Agents for Code Review](https://mlsanity.com/paper/2402.02172/) (2024)
- [Process-Centric Analysis of Agentic Software Systems](https://mlsanity.com/paper/2512.02393/) (2025)
- [BitsAI-CR: Automated Code Review via LLM in Practice](https://mlsanity.com/paper/2501.15134/) (2025)
- [Code Review Automation: Strengths and Weaknesses of the State of the Art](https://mlsanity.com/paper/2401.05136/) (2024)
- [Rethinking Code Review Workflows with LLM Assistance: An Empirical Study](https://mlsanity.com/paper/2505.16339/) (2025)
- [LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM](https://mlsanity.com/paper/2512.01356/) (2025)
- [An Empirical Study on Code Review Activity Prediction and Its Impact in Practice](https://mlsanity.com/paper/2404.10703/) (2024)
- [Targeted Testing of Compiler Optimizations via Grammar-Level Composition Styles](https://mlsanity.com/paper/2512.04344/) (2025)

## Abstract (arXiv)

Modern compilers are frequently updated, but expert review capacity is highly limited, leading to delayed integration and, in some cases, subtle semantic bugs entering the compiler codebase. Automating the code review process with modern general code review agents may be feasible, but it faces critical challenges due to compiler complexity. In this paper, we use LLVM as our target compiler and present Archer, the first automated agentic code review tool for compiler optimizations. Archer constrains the agentic review process from both ends by using obligations to guide analysis and a deterministic validation guard to admit only findings backed by executable evidence. We evaluated Archer on 70 open PRs and 328 closed PRs in LLVM from the last two months. The review results are shocking and concerning: Archer discovers that 21% of open PRs and 11% of closed PRs are buggy, i.e, introducing semantic bugs such as miscompilations in LLVM. Our findings expose a critical gap in the capacity for critical review in large compiler projects and demonstrate the practical value of Archer as an additional reviewer.