7 papers
The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages
Zixuan Wu, Carolyn Jane Anderson, Arjun Guha
Although coding agents are now very effective in a variety of programming languages, this paper first shows that the cost (in tokens) can very significantly by programming language…
Learning Reasoning World Models for Parallel Code
Gautam Singh, Arjun Guha, Bhavya Kailkhura +1
Large language models have shown remarkable ability in serial code generation, but they still struggle with parallel code for which training data is comparatively scarce. A common…
AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Yangtian Zi, Zixuan Wu, Aleksander Boruch-Gruszecki +2
Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human int…
Steering Code LLMs with Activation Directions for Language and Library Control
Md Mahbubur Rahman, Arjun Guha, Harshitha Menon
Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear direct…
Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment
Aleksander Boruch-Gruszecki, Yangtian Zi, Zixuan Wu +4
Large language models (LLMs) already excel at writing code in high-resource languages such as Python and JavaScript, yet stumble on low-resource languages that remain essential to…
ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models
Zixuan Wu, Francesca Lucchetti, Aleksander Boruch-Gruszecki +5
Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 probl…