arXiv Computation and Language October 22, 2026 By Zixuan Wu, Carolyn Jane Anderson, Arjun Guha

The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages

Read the original on arXiv Computation and Language →

The paper investigates how token consumption varies across programming languages for coding agents. Five recent models were evaluated on Python, Java, Rust, and OCaml, revealing significant differences in token usage that persist across models. Analysis of agent trajectories shows that agents often generate non‑compiling solutions in unfamiliar languages, revise passing solutions, plan in code comments, distrust provided tests, and prototype in Python to sidestep unfamiliar languages.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jun 10

Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages

arXiv:2606. 10933v1 Announce Type: new Abstract: LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories.

By Aman Sharma, Sushrut Thorat, Paras Chopra

llms agents benchmarks

arXiv Computation and Language

Sep 17

LangSelect: Cost-Aware Target-Language Routing for LLM Code Generation

arXiv:2609.18959v1 Announce Type: new Abstract: LLM code-generation systems usually choose a target programming language before decoding and treat that choice as fixed. We show that, for language-fle...

By Son Ha Xuan, Phat T. Tran-Truong, Xuan-Bach Le, Nghia Duong-Trung

llms

arXiv AI

Aug 14

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

arXiv:2603. 14501v2 Announce Type: replace-cross Abstract: Large Language Models excel in high-resource programming languages but struggle with low-resource ones.

By Junhang Cheng, Fang Liu, Jia Li, Chengru Wu, Nanxiang Jiang, Li Zhang

llms rag agents benchmarks

arXiv AI

Jul 17

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

arXiv:2607. 14816v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias.

By Saima Afrin, Alessandro Midolo, Camilo Escobar-Vel\'asquez, Mario Linares-V\'asquez, Weiyuan Ding, Bowen Xu, Massimiliano Di Penta, Antonio Mastropaolo

llms benchmarks safety

Hugging Face Trending Papers

Jul 16

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general text generation, its impact on code generation quality and programming conventions remains largely unexplored.

llms benchmarks safety

arXiv AI

Jun 3

Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing

arXiv:2606. 03618v1 Announce Type: new Abstract: AI-assisted coding agents are bottlenecked by input-token cost.

By Mehmet Utku Colak

llms agents nlp benchmarks

One email a morning, machine-written

Related stories

Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages

LangSelect: Cost-Aware Target-Language Routing for LLM Code Generation

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing