English
Related papers

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

200 papers

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…

Computation and Language · Computer Science 2026-05-21 Wujiang Xu , Yu Wang , Kai Mei , Kaiqu Liang , Zhenting Wang , Mingyu Jin , Han Zhang , Shi-Xiong Zhang , Wenyue Hua , Sambit Sahu , Dimitris N. Metaxas

In this paper, we introduce SWE-QA, a text and code corpus aimed at benchmarking multi-hop code comprehension, addressing the gap between simplified evaluation tasks and the complex reasoning required in real-world software development.…

Software Engineering · Computer Science 2026-04-29 Laïla Elkoussy , Julien Perez

While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. We propose to create a shared agent-entity graph, where agents and environmental entities form vertices,…

Machine Learning · Computer Science 2019-06-05 Akshat Agarwal , Sumit Kumar , Katia Sycara

Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language. To what extent can LLMs generalize across these…

Computation and Language · Computer Science 2026-02-04 Fangru Lin , Valentin Hofmann , Xingchen Wan , Weixing Wang , Zifeng Ding , Anthony G. Cohn , Janet B. Pierrehumbert

We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends. It enables two capabilities previously out of reach for…

Artificial Intelligence · Computer Science 2026-05-28 Dingbang Wu , Rui Hao , Haiyang Wang , Shuzhe Wu , Han Xiao , Zhenghong Li , Bojiang Zhou , Zheng Ju , Zichen Liu , Lue Fan , Zhaoxiang Zhang

Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques…

Machine Learning · Computer Science 2020-12-01 Jake Grigsby , Yanjun Qi

Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in…

Artificial Intelligence · Computer Science 2023-09-20 Wenjun Li , Pradeep Varakantham , Dexun Li

GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia. Within this task, SWE-bench has been released to evaluate issue resolving capabilities of large…

Due to the realization that deep reinforcement learning algorithms trained on high-dimensional tasks can strongly overfit to their training environments, there have been several studies that investigated the generalization performance of…

Machine Learning · Computer Science 2020-07-06 Safa Alver , Doina Precup

Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains…

Software Engineering · Computer Science 2026-02-10 Qinglin Zhu , Tianyu Chen , Shuai Lu , Lei Ji , Runcong Zhao , Murong Ma , Xiangxiang Dai , Yulan He , Lin Gui , Peng cheng , Yeyun Gong

The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks…

Software Engineering · Computer Science 2026-01-19 Jie Yang , Honglin Guo , Li Ji , Jiazheng Zhou , Rui Zheng , Zhikai Lei , Shuo Zhang , Zhiheng Xi , Shichun Liu , Yuxin Wang , Bo Wang , Yining Zheng , Tao Gui , Xipeng Qiu

We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development…

Computation and Language · Computer Science 2025-06-12 Lei Zhang , Jiaxi Yang , Min Yang , Jian Yang , Mouxiang Chen , Jiajun Zhang , Zeyu Cui , Binyuan Hui , Junyang Lin

Large Language Model (LLM)-based agents have emerged as a new paradigm that extends LLMs' capabilities beyond text generation to dynamic interaction with external environments. By integrating reasoning with perception, memory, and tool use,…

Artificial Intelligence · Computer Science 2025-09-23 Minxing Zhang , Yi Yang , Roy Xie , Bhuwan Dhingra , Shuyan Zhou , Jian Pei

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Artificial Intelligence · Computer Science 2026-04-08 Hangoo Kang , Tarun Suresh , Jon Saad-Falcon , Azalia Mirhoseini

Recent studies operationalize self-improvement through coding agents that edit their own codebases. They grow a tree of self-modifications through expansion strategies that favor higher software engineering benchmark performance, assuming…

Artificial Intelligence · Computer Science 2025-10-30 Wenyi Wang , Piotr Piękos , Li Nanbo , Firas Laakom , Yimeng Chen , Mateusz Ostaszewski , Mingchen Zhuge , Jürgen Schmidhuber

To survive and thrive in complex environments, humans have evolved sophisticated self-improvement mechanisms through environment exploration, hierarchical abstraction of experiences into reuseable skills, and collaborative construction of…

Artificial Intelligence · Computer Science 2025-04-10 Boyuan Zheng , Michael Y. Fatemi , Xiaolong Jin , Zora Zhiruo Wang , Apurva Gandhi , Yueqi Song , Yu Gu , Jayanth Srinivasa , Gaowen Liu , Graham Neubig , Yu Su

Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…

Computation and Language · Computer Science 2024-09-12 Zora Zhiruo Wang , Jiayuan Mao , Daniel Fried , Graham Neubig

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we…

Artificial Intelligence · Computer Science 2026-03-13 Aniketh Garikaparthi , Manasi Patwardhan , Arman Cohan

As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code…

Computation and Language · Computer Science 2026-03-05 Dadi Guo , Yuejin Xie , Qingyu Liu , Jiayu Liu , Zhiyuan Fan , Qihan Ren , Shuai Shao , Tianyi Zhou , Dongrui Liu , Yi R. Fung

Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing benchmarks prioritize reproducibility but are often limited to open-source apps or…

Artificial Intelligence · Computer Science 2026-05-26 Guohong Liu , Jialei Ye , Pengzhi Gao , Wei Liu , Jian Luan , Yunxin Liu , Yuanchun Li