English
Related papers

Related papers: Immersion in the GitHub Universe: Scaling Coding A…

200 papers

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this…

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,…

Agents based on large language models have recently shown strong potential on real-world software engineering (SWE) tasks that require long-horizon interaction with repository-scale codebases. However, most existing agents rely on…

Computation and Language · Computer Science 2025-12-29 Shukai Liu , Jian Yang , Bo Jiang , Yizhi Li , Jinyang Guo , Xianglong Liu , Bryan Dai

Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and…

Artificial Intelligence · Computer Science 2026-03-18 Yulin Peng , Xinxin Zhu , Chenxing Wei , Nianbo Zeng , Leilei Wang , Ying Tiffany He , F. Richard Yu

Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation,…

OpenClaw's ClawHub marketplace hosts tens of thousands of community-contributed agent skills (49,592 in our 2026-04-04 snapshot), and recent audits report that 13-26% contain security vulnerabilities. Regex scanners miss obfuscated…

Cryptography and Security · Computer Science 2026-05-27 Yinghan Hou , Zongyou Yang , Zaihu Pang , Xiujun Ma

In the era of data-driven decision-making, the complexity of data analysis necessitates advanced expertise and tools of data science, presenting significant challenges even for specialists. Large Language Models (LLMs) have emerged as…

Artificial Intelligence · Computer Science 2024-02-28 Yuge Zhang , Qiyang Jiang , Xingyu Han , Nan Chen , Yuqing Yang , Kan Ren

We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes,…

Software Engineering · Computer Science 2026-01-23 Kevin Han , Siddharth Maddikayala , Tim Knappe , Om Patel , Austen Liao , Amir Barati Farimani

Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the…

Computation and Language · Computer Science 2026-02-04 Ziyang Huang , Haolin Ren , Xiaowei Yuan , Jiawei Wang , Zhongtao Jiang , Kun Xu , Shizhu He , Jun Zhao , Kang Liu

Static program slicing, which extracts the executable portions of a program that affect the values at a specific location, supports many software analysis tasks such as debugging and security auditing. However, traditional slicing tools…

Software Engineering · Computer Science 2025-07-28 Jianming Chang , Jieke Shi , Yunbo Lyu , Xin Zhou , Lulu Wang , Zhou Yang , Bixin Li , David Lo

Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings. Yet existing data science benchmarks fall short due to fragmented evaluation interfaces that make…

Artificial Intelligence · Computer Science 2026-01-26 Fan Nie , Junlin Wang , Harper Hua , Federico Bianchi , Yongchan Kwon , Zhenting Qi , Owen Queen , Shang Zhu , James Zou

Large Language Models (LLMs) have revolutionized natural language interaction with data. The "holy grail" of data analytics is to build autonomous Data Agents that can self-drive complex data analysis workflows. However, current…

Databases · Computer Science 2026-04-01 Boyan Li , Yiran Peng , Yupeng Xie , Sirong Lu , Yizhang Zhu , Xing Mu , Xinyu Liu , Yuyu Luo

Environments are the bottleneck for self-improving agents. Current terminal benchmarks were built for evaluation, not training; reinforcement learning requires a scalable pipeline, not just a dataset. We introduce Endless Terminals, a fully…

Machine Learning · Computer Science 2026-02-17 Kanishk Gandhi , Shivam Garg , Noah D. Goodman , Dimitris Papailiopoulos

Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…

Artificial Intelligence · Computer Science 2026-05-29 Tenghao Huang , Kung-Hsiang Huang , Prafulla Kumar Choubey , Yilun Zhou , Muhao Chen , Jonathan May , Chien-Sheng Wu

Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to…

Computation and Language · Computer Science 2025-12-29 KaShun Shum , Binyuan Hui , Jiawei Chen , Lei Zhang , X. W. , Jiaxi Yang , Yuzhen Huang , Junyang Lin , Junxian He

The rapid growth of scientific literature demands robust tools for automated survey-generation. However, current large language model (LLM)-based methods often lack in-depth analysis, structural coherence, and reliable citations. To address…

Artificial Intelligence · Computer Science 2025-07-22 Xiaofeng Shi , Qian Kou , Yuduo Li , Ning Tang , Jinxin Xie , Longbin Yu , Songjing Wang , Hua Zhou

Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evaluate code agents in such authentic, workflow-driven scenarios.…

Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on manually curated rules and workflows, which cannot adapt to…

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…

Computation and Language · Computer Science 2026-03-10 Zongqian Li , Tengchao Lv , Shaohan Huang , Yixuan Su , Qinzheng Sun , Qiufeng Yin , Ying Xin , Scarlett Li , Lei Cui , Nigel Collier , Furu Wei
‹ Prev 1 8 9 10 Next ›