English
Related papers

Related papers: Hybrid-Gym: Training Coding Agents to Generalize A…

200 papers

Recent work synthesizes agentic tasks for post-training tool-using LLMs, yet robust generalization under shifts in tasks and toolsets remains an open challenge. We trace this brittleness to insufficient diversity in synthesized tasks.…

Artificial Intelligence · Computer Science 2026-03-13 Aili Chen , Chi Zhang , Junteng Liu , Jiangjie Chen , Chengyu Du , Yunji Li , Ming Zhong , Qin Wang , Zhengmao Zhu , Jiayuan Song , Ke Ji , Junxian He , Pengyu Zhao , Yanghua Xiao

As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via…

Computation and Language · Computer Science 2026-04-07 Yuhang Zhou , Lizhu Zhang , Yifan Wu , Jiayi Liu , Xiangjun Fan , Zhuokai Zhao , Hong Yan

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current…

Software Engineering · Computer Science 2026-02-12 Qixing Zhou , Jiacheng Zhang , Haiyang Wang , Rui Hao , Jiahe Wang , Minghao Han , Yuxue Yang , Shuzhe Wu , Feiyang Pan , Lue Fan , Dandan Tu , Zhaoxiang Zhang

AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to…

Computation and Language · Computer Science 2026-03-24 Jiayi Geng , Graham Neubig

One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of model-based agents…

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…

Machine Learning · Computer Science 2026-05-01 Henrik Voigt , Michael Habeck , Joachim Giesen

While reinforcement learning (RL) can empower autonomous agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and…

Large language models are quickly becoming the foundation for intelligent agents that are capable of using tools. However, training such agents is challenging because it requires human creation and annotation of a diverse set of tasks,…

Artificial Intelligence · Computer Science 2025-06-03 Yifei Zhou , Sergey Levine , Jason Weston , Xian Li , Sainbayar Sukhbaatar

Large Language Models (LLMs) in Software Engineering (SE) can offer assistance for coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al. introduced the SWE-bench dataset, which comprises 2,294…

Software Engineering · Computer Science 2024-10-11 Reem Aleithan , Haoran Xue , Mohammad Mahdi Mohajer , Elijah Nnorom , Gias Uddin , Song Wang

This paper presents a hybrid approach to predict the evolution of technological maturity in R and D projects, using the oil and gas sector as an example. Integrating System Dynamics (SD) and Agent Based Modelling (ABM) allows the proposed…

Multiagent Systems · Computer Science 2025-10-14 R. W. S. Pessoa , M. H. Næss , J. C. Bijos , C. M. Rebello , D. Colombo , L. Schnitman , I. B. R. Nogueira

The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination…

Software engineering (SE) is increasingly collaborative, with developers working together on shared complex codebases. Effective collaboration in shared environments requires participants -- whether humans or AI agents -- to stay on the…

Software Engineering · Computer Science 2025-06-10 Xuehang Guo , Xingyao Wang , Yangyi Chen , Sha Li , Chi Han , Manling Li , Heng Ji

Existing datasets for coding agents evaluate performance on isolated, single pull request (PR) tasks in a stateless manner, failing to capture the reality of real-world software development where code changes accumulate, technical debt…

Software Engineering · Computer Science 2026-04-06 KN Ajay Shastry , Ganesh Senrayan , Shrey Satapara , Pranoy Panda , Chaitanya Devaguptapu

The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…

Software Engineering · Computer Science 2025-11-04 Oorja Majgaonkar , Zhiwei Fei , Xiang Li , Federica Sarro , He Ye

Recent advances in coding agents have made them capable of planning, editing, running, and testing complex code bases. Despite their growing ability in coding tasks, these systems still struggle to infer and track user intent, especially…

Software Engineering · Computer Science 2026-02-02 Xuhui Zhou , Valerie Chen , Zora Zhiruo Wang , Graham Neubig , Maarten Sap , Xingyao Wang

Modern human labor is characterized by specialization; we train for years and develop particular tools that allow us to perform well across a variety of tasks. In addition, AI agents have been specialized for domains such as software…

Computation and Language · Computer Science 2025-06-04 Aditya Bharat Soni , Boxuan Li , Xingyao Wang , Valerie Chen , Graham Neubig

We introduce SWE-Bench Pro, a substantially more challenging benchmark that builds upon the best practices of SWE-BENCH [25], but is explicitly designed to capture realistic, complex, enterprise-level problems beyond the scope of SWE-BENCH.…

Automating real-world software engineering tasks remains challenging for large language model (LLM)-based agents due to the need for long-horizon reasoning over large, evolving codebases and making consistent decisions across interdependent…

Software Engineering · Computer Science 2026-04-14 Mahir Labib Dihan , Md Ashrafur Rahman Khan

As coding agents have seen rapid capability and adoption gains, users are applying them to general tasks beyond software engineering. In this post, we investigate whether coding agents can successfully generalize to end-to-end business…

Software Engineering · Computer Science 2026-04-16 Maksim Ivanov , Abhijay Rana , Gokul Prabhakaran

Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orchestrate tools for such rigorous workflows. To bridge this gap,…

‹ Prev 1 3 4 5 6 7 10 Next ›