mlsanityData to 14 Oct 2026

Archer: Towards Agentic Review for Compiler Optimizations

arXiv 2607.01808 ↗First posted 2 Jul 2026cs.SEcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

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.

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.

Builds on

14 of 49 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Process-Centric Analysis of Agentic Software Systems2 Dec
  2. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May
  3. 2024CodeAgent: Autonomous Communicative Agents for Code Review3 Feb

Other references · 11

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  3. 2024Are self-explanations from Large Language Models faithful?cited by 101
  4. 2025Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineeringcited by 67
  5. 2026CL-bench: A Benchmark for Context Learningcited by 47
  6. 2025BitsAI-CR: Automated Code Review via LLM in Practicecited by 22
  7. 2024Code Review Automation: Strengths and Weaknesses of the State of the Artcited by 20
  8. 2025Rethinking Code Review Workflows with LLM Assistance: An Empirical Studycited by 10
  9. 2025LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLMcited by 8
  10. 2024An Empirical Study on Code Review Activity Prediction and Its Impact in Practicecited by 1
  11. 2025Targeted Testing of Compiler Optimizations via Grammar-Level Composition Stylescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Understanding Agent-Based Patching of Compiler Missed Optimizations
  2. 2026Can Coding Agents Implement Missed Compiler Optimizations? Evaluating LLM Agents on LLVM Peephole Optimizations
  3. 2026AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
  4. 2025AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
  5. 2025Agentic Auto-Scheduling: An Experimental Study of LLM-Guided Loop Optimization
  6. 2026OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review
  7. 2026LiteCoOp: Lightweight Multi-LLM Shared-Tree Reasoning for Model-Serving Compiler Optimizations
  8. 2025Large Language Model Critics for Execution-Free Evaluation of Code Changes