English
Related papers

Related papers: Debugging code world models

200 papers

Imitation learning practitioners have often noted that conditioning policies on previous actions leads to a dramatic divergence between "held out" error and performance of the learner in situ. Interactive approaches can provably address…

Machine Learning · Computer Science 2021-02-12 Jonathan Spencer , Sanjiban Choudhury , Arun Venkatraman , Brian Ziebart , J. Andrew Bagnell

Transformer language models (LMs) exhibit behaviors -- from storytelling to code generation -- that seem to require tracking the unobserved state of an evolving world. How do they do this? We study state tracking in LMs trained or…

Computation and Language · Computer Science 2025-11-03 Belinda Z. Li , Zifan Carl Guo , Jacob Andreas

As large language models become increasingly capable of generating code, evaluating their performance remains a complex and evolving challenge. Existing benchmarks primarily focus on functional correctness, overlooking the diversity of…

Software Engineering · Computer Science 2025-11-03 Forough Mehralian , Ryan Shar , James R. Rae , Alireza Hashemi

Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the generated programs.…

Software Engineering · Computer Science 2024-06-12 Li Zhong , Zilong Wang , Jingbo Shang

Reinforcement learning (RL) agents have shown remarkable performances in various environments, where they can discover effective policies directly from sensory inputs. However, these agents often exploit spurious correlations in the…

Artificial Intelligence · Computer Science 2025-04-11 Elisabeth Dillies , Quentin Delfosse , Jannis Blüml , Raban Emunds , Florian Peter Busch , Kristian Kersting

To close the gap between LLM-based agents and humans in planning and reasoning, agents need large-scale, diverse environments for continuous learning -- yet building such environments is itself prohibitively expensive. We present C-World,…

Artificial Intelligence · Computer Science 2026-04-21 Ziqiao Xi , Shuang Liang , Qi Liu , Jiaqing Zhang , Letian Peng , Fang Nan , Meshal Nayim , Tianhui Zhang , Rishika Mundada , Lianhui Qin , Biwei Huang , Kun Zhou

Most vulnerability detection studies focus on datasets of vulnerabilities in C/C++ code, offering limited language diversity. Thus, the effectiveness of deep learning methods, including large language models (LLMs), in detecting software…

Software Engineering · Computer Science 2026-02-18 Kohei Dozono , Tiago Espinha Gasiba , Andrea Stocco

Code reasoning tasks are increasingly crucial to evaluating large language models (LLMs). Yet most existing benchmarks rely on simplistic, LLM-generated snippets or human-written solutions to code challenges and often restrict inputs and…

Software Engineering · Computer Science 2026-04-15 Changshu Liu

Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their performance often deteriorates sharply in long-horizon tasks, exhibiting systematic breakdown beyond certain scales. Conventional explanations primarily…

Artificial Intelligence · Computer Science 2026-02-09 Hsien-Jyh Liao

We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of…

Machine Learning · Computer Science 2024-08-06 Charles Jin , Martin Rinard

Logging code is written by developers to capture system runtime behavior and plays a vital role in debugging, performance analysis, and system monitoring. However, defects in logging code can undermine the usefulness of logs and lead to…

Software Engineering · Computer Science 2025-08-18 Xin Wang , Zhenhao Li , Zishuo Ding

Long chain-of-thought (CoT) supervision has become a common strategy to enhance reasoning in language models. While effective for large models, we identify a phenomenon we call Long CoT Degradation, in which small language models (SLMs;…

Computation and Language · Computer Science 2025-10-02 Renjie Luo , Jiaxi Li , Chen Huang , Wei Lu

Conducting usability testing like cognitive walkthrough (CW) can be costly. Recent developments in large language models (LLMs), with visual reasoning and UI navigation capabilities, present opportunities to automate CW. We explored whether…

Human-Computer Interaction · Computer Science 2025-12-04 Ruican Zhong , David W. McDonald , Gary Hsieh

Weak memory models specify the semantics of concurrent programs on multi-core architectures. Reasoning techniques for weak memory models are often specialized to one fixed model and verification results are hence not transferable to other…

Logic in Computer Science · Computer Science 2023-09-07 Lara Bargmann , Heike Wehrheim

Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable prediction of action consequences remains critical for long-horizon and high-risk…

Artificial Intelligence · Computer Science 2026-05-25 Weikai Xu , Kun Huang , Yunren Feng , Jiaxing Li , Yuhan Chen , Yuxuan Liu , Zhizheng Jiang , Heng Qu , Pengzhi Gao , Wei Liu , Jian Luan , Xiaolin Hu , Bo An

This study investigates the reliability of code generation by Large Language Models (LLMs), focusing on identifying and analyzing defects in the generated code. Despite the advanced capabilities of LLMs in automating code generation,…

Software Engineering · Computer Science 2024-08-27 Ali Mohammadi Esfahani , Nafiseh Kahani , Samuel A. Ajila

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied…

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…

Artificial Intelligence · Computer Science 2025-06-10 Ming Liu , Wensheng Zhang

Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…

Cryptography and Security · Computer Science 2025-02-14 Karl Tamberg , Hayretdin Bahsi

Large Language Models (LLMs) have recently demonstrated strong capabilities in code-related tasks, but their robustness in code reasoning under perturbations remains underexplored. We introduce CodeCrash, a stress-testing framework with…

Artificial Intelligence · Computer Science 2025-10-14 Man Ho Lam , Chaozheng Wang , Jen-tse Huang , Michael R. Lyu