The paper introduces Brittlebench, a framework and evaluation pipeline that measures how sensitive large language models (LLMs) are to prompt variations. By applying semantics‑preserving perturbations to popular benchmarks, the authors show that model performance can drop by up to 12% and that such perturbations can change model rankings in 63% of cases. The study finds that these input variations can explain up to half of the performance variance for a given model, underscoring the importance of robust evaluation methods.
By Angelika Romanou, Mark Ibrahim, Candace Ross, Kerem Oktar, Chantal Shaib, Samuel J. Bell, Anaelia Ovalle, Antoine Bosselut, Jesse Dodge, Koustuv Sinha, Adina Williams
arXiv:2608. 03983v1 Announce Type: cross Abstract: Optimizing compilers miss profitable transformations when their enabling semantics are absent from the analyzed program representation.
By Hailong Jiang, Feng Yu, Emran Hossain, Jianfeng Zhu, Mengfei Ren, Qiang Guan, Chunwei Xia
arXiv:2608. 08700v1 Announce Type: new Abstract: Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents.
By Dongjie Xu, Julius, Hanchi Dong, Minghua Tang, Yuxuan Sun, Ziwei Nie, Zicheng Liu, Dujun Qing, Jiajie Xu
arXiv:2607. 18642v1 Announce Type: new Abstract: Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface "messiness," and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set.
By Yuxiang Ji
AI code agents are increasingly deployed to resolve real software issues, yet their reliability under superficial code variations remains poorly understood. We evaluate whether coding agents that repa...
arXiv:2610.07070v1 Announce Type: new
Abstract: Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool call...
By Aaron Fainman, Gabriela Kadlecov\'a, Maciej Gryka, Bartosz Kruszczy\'nski, Usman Zafar, C\'edric Archambeau, Aaron Klein, David Salinas, Selim Nowicki, Jacek Golebiowski
The paper investigates whether intrinsic tokenizer features can predict the performance of downstream language models. By training about 200 models across nine languages and evaluating numerous tokenizer metrics, the authors find that none of the existing metrics consistently forecasts model performance across different families, tasks, and languages. They propose a new linguistically grounded metric that captures aspects of tokenizer quality missed by prior measures, though its predictive power may still vary.
By Antonio Lopardo, Luis Frentzen Salim, Shikhar Srivastava, Kevin Jiang, Mridul Sharma, Catherine Arnett
arXiv:2512. 03086v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data are scarce.
By Le Chen, Nuo Xu, Winson Chen, Bin Lei, Pei-Hung Lin, Dunzhi Zhou, Rajeev Thakur, Caiwen Ding, Ali Jannesari, Chunhua Liao
The paper introduces Program Executability Prediction (PrEx), a task that asks large language models (LLMs) to determine whether a program is semantically valid or invalid and, if invalid, to identify the violated formal rule. To evaluate this, the authors create a dataset of systematically generated invalid programs derived from valid ones and test open‑source coding LLMs across different semantic formalisms, semantic shifts, and program splits (human‑written, LLM‑translated, fuzzer‑generated). Results show that LLMs rely more on pre‑training priors than on the provided semantics, performing poorly on modified semantics and with increasing program complexity.
By Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric
arXiv:2607. 24717v1 Announce Type: cross Abstract: Pretraining data processing is critical to the downstream performance of Large Language Models (LLMs).
By Zhen Huang, Yikun Wang, Shijie Xia, Pengfei Liu
The paper introduces SWE-Flux, a repository‑level benchmark designed to test large language models’ ability to reason about runtime behavior. It contains 480 execution‑grounded instances from 12 real Python repositories, with gold answers automatically harvested from instrumented test executions. Evaluation of five LLMs shows the task remains difficult, with the best model achieving only 37% accuracy, and the benchmark can generate challenging variants through input perturbation.
By Hamed Taherkhani, Mohammad Abdollahi, Melika Sepidband, Hridya Dhulipala, Tien N. Nguyen, Hadi Hemmati
arXiv:2603. 15510v2 Announce Type: replace Abstract: The synthesis of inductive loop invariants remains a critical bottleneck in automated program verification.
By Ido Pinto, Yizhak Yisrael Elboher, Haoze Wu, Nina Narodytska, Guy Katz