From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python

• URL: http://arxiv.org/abs/2604.11518v1
• Date: Mon, 13 Apr 2026 14:21:44 GMT
• Title: From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python
• Abstract summary: We present a methodology for LLM-assisted continuous code translation in which a large language model translates a production Rust objective into Python.<n>We demonstrate that the Python port resolves 59/80 SWE-bench Verified tasks (73.8%) versus Rust's 56/80 (70.0%), confirming near-parity on real-world agentic tasks.<n>Our evaluation shows that for LLM-based agents where API latency dominates, Python's expressiveness yields a 15.9x code reduction with negligible performance cost.
• Score: 2.7324157162184157
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-language migration of large software systems is a persistent engineering challenge, particularly when the source codebase evolves rapidly. We present a methodology for LLM-assisted continuous code translation in which a large language model translates a production Rust codebase (648K LOC, 65 crates) into Python (41K LOC, 28 modules), with public agent benchmarks as the objective function driving iterative refinement. Our subject system is Codex CLI, a production AI coding agent. We demonstrate that: (1) the Python port resolves 59/80 SWE-bench Verified tasks (73.8%) versus Rust's 56/80 (70.0%), and achieves 42.5% on Terminal-Bench versus Rust's 47.5%, confirming near-parity on real-world agentic tasks; (2) benchmark-driven debugging, revealing API protocol mismatches, environment pollution, a silent WebSocket failure mode, and an API 400 crash, is more effective than static testing alone; (3) the architecture supports continuous upstream synchronisation via an LLM-assisted diff-translate-test loop; and (4) the Python port has evolved into a capability superset with 30 feature-flagged extensions (multi-agent orchestration, semantic memory, guardian safety, cost tracking) absent from Rust, while preserving strict parity mode for comparison. Our evaluation shows that for LLM-based agents where API latency dominates, Python's expressiveness yields a 15.9x code reduction with negligible performance cost, while the benchmark-as-objective-function methodology provides a principled framework for growing a cross-language port from parity into an extended platform.

Related papers

• Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures [4.307697295291473]
  Axon is a strongly typed domain-specific language with Haskell-like syntax.<n>By basing collaboration on a language specification rather than a specific framework's vision, Axon fosters open cooperation.<n>In 467 benchmarking experiments on models ranging from 135M to 32B parameters, we demonstrate median speedups of 7% on PyTorch, 12% on PyTorch with Triton, 91% on JAX, and 107% on MLX.
  arXiv  Detail & Related papers  (2026-08-20T10:56:34Z)
• RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications [0.0]
  RuBench 1.0 is a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories.<n>Each task is specified in Russian, written from scratch in the style of an actual customer request, not translated.<n>All 25 fix commits postdate the training-data cutoffs of every evaluated model.
  arXiv  Detail & Related papers  (2026-07-07T15:41:22Z)
• WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation [88.10947115397971]
  This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories.<n>Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls.<n> Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification.
  arXiv  Detail & Related papers  (2026-05-11T17:49:43Z)
• ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents [77.22389710754452]
  We introduce bench, a benchmark for coworker agents built around multi-turn multi-day tasks.<n>The current release contains 100 tasks across 13 professional scenarios, executed against five stateful sandboxed services.<n>The strongest model reaches 75.8 weighted score, but the best strict Task Success is only 20.0%, indicating that partial progress is common.
  arXiv  Detail & Related papers  (2026-04-26T16:05:02Z)
• RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository [52.98970048197381]
  RepoGenesis is the first multilingual benchmark for repository-level end-to-end web microservice generation.<n>It consists of 106 repositories (60 Python, 46 Java) across 18 domains and 11 frameworks, with 1,258 API endpoints and 2,335 test cases verified.<n>Results reveal that despite high AC (up to 73.91%) and DSR (up to 100%), the best-performing system achieves only 23.67% Pass@1 on Python and 21.45% on Java.
  arXiv  Detail & Related papers  (2026-01-20T13:19:20Z)
• Anka: A Domain-Specific Language for Reliable LLM Code Generation [0.0]
  Large Language Models (LLMs) exhibit systematic errors on complex, multi-step programming tasks.<n>We introduce Anka, a domain-specific language () for data transformation pipelines designed with explicit, constrained syntax.<n>Anka achieves 99.9% parse success and 95.8% overall task accuracy across 100 benchmark problems.
  arXiv  Detail & Related papers  (2025-12-29T05:28:17Z)
• A Multi-Language Object-Oriented Programming Benchmark for Large Language Models [61.267115598083315]
  A survey of 35 existing benchmarks uncovers three major imbalances.<n>85.7% focus on a single programming language.<n>94.3% target only function-level or statement-level tasks.<n>Over 80% include fewer than ten test cases on average.
  arXiv  Detail & Related papers  (2025-09-30T11:30:08Z)
• RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation [28.156862491709237]
  RustEvo is a framework for evaluating the ability of large language models to adapt to evolving Rust APIs.<n>It automates dataset creation by synthesizing 588 API changes into programming tasks mirroring real-world challenges.<n>Experiments on state-of-the-art (SOTA) LLMs reveal significant performance variations.
  arXiv  Detail & Related papers  (2025-03-21T07:33:59Z)
• RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust [50.65321080814249]
  RustRepoTrans is the first repository-level context code translation benchmark targeting incremental translation.<n>We evaluate seven representative LLMs, analyzing their errors to assess limitations in complex translation scenarios.
  arXiv  Detail & Related papers  (2024-11-21T10:00:52Z)
• CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution [50.1875460416205]
  The CRUXEVAL-X code reasoning benchmark contains 19 programming languages.<n>It comprises at least 600 subjects for each language, along with 19K content-consistent tests in total.<n>Even a model trained solely on Python can achieve at most 34.4% Pass@1 in other languages.
  arXiv  Detail & Related papers  (2024-08-23T11:43:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.