65 citations · 136 across the 30 of their papers we have counts for
31 papers
EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup
Hanwu Chen, Hanyu Lin, Zhanjiang Yang +6
Environment Setup is a critical yet complex task in software engineering that relies heavily on expert knowledge. Existing automated environment setup methods lack the ability to a…
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
Jingzhe Ding, Shengda Long, Changxin Pu +46
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities re…
AInsteinBench: Benchmarking Coding Agents on Scientific Repositories
Titouan Duston, Shuo Xin, Yang Sun +26
We introduce AInsteinBench, a large-scale benchmark for evaluating whether large language model (LLM) agents can operate as scientific computing development agents within real rese…
From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence
Jian Yang, Xianglong Liu, Weifeng Lv +68
Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, dri…
Virtual Width Networks
Seed, Baisheng Li, Banggu Wu +115
We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…
SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories
Junhao Wang, Daoguang Zan, Shulin Xin +3
Creating large-scale verifiable training datasets for issue-resolving tasks is a critical yet notoriously difficult challenge. Existing methods on automating the Gym environment se…
AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions
Zihan Wang, Jiaze Chen, Zhicheng Liu +25
Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on exi…
Seed-Coder: Let the Code Model Curate Data for Itself
ByteDance Seed, Yuyu Zhang, Jing Su +24
Code data in large language model (LLM) pretraining is recognized crucial not only for code-related tasks but also for enhancing general intelligence of LLMs. Current open-source L…
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
Daoguang Zan, Zhirong Huang, Wei Liu +16
The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on P…
CodeV: Issue Resolving with Visual Data
Linhao Zhang, Daoguang Zan, Quanshun Yang +10
Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks. GitHub issue r…
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Bofei Gao, Feifan Song, Yibo Miao +22
Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This align…
Aligning CodeLLMs with Direct Preference Optimization
Yibo Miao, Bofei Gao, Shanghaoran Quan +6
The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not…
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
Bofei Gao, Feifan Song, Zhe Yang +17
Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH ar…
Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment
Yan Liu, Xiaoyuan Yi, Xiaokang Chen +6
The demand for regulating potentially risky behaviors of large language models (LLMs) has ignited research on alignment methods. Since LLM alignment heavily relies on reward models…
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
Daoguang Zan, Zhirong Huang, Ailun Yu +17
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 releas…
The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models
Yan Liu, Yu Liu, Xiaokang Chen +4
Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic…
CodeR: Issue Resolving with Multi-Agent and Task Graphs
Dong Chen, Shaoxin Lin, Muhan Zeng +14
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,…
GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
Wei Liu, Ailun Yu, Daoguang Zan +5
The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code…
CodeS: Natural Language to Code Repository via Multi-Layer Sketch
Daoguang Zan, Ailun Yu, Wei Liu +11
The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a n…
Improving Natural Language Capability of Code Large Language Model
Wei Li, Daoguang Zan, Bei Guan +3
Code large language models (Code LLMs) have demonstrated remarkable performance in code generation. Nonetheless, most existing works focus on boosting code LLMs from the perspectiv…
A GAN-based data poisoning framework against anomaly detection in vertical federated learning
Xiaolin Chen, Daoguang Zan, Wei Li +2
In vertical federated learning (VFL), commercial entities collaboratively train a model while preserving data privacy. However, a malicious participant's poisoning attack may degra…
Can Programming Languages Boost Each Other via Instruction Tuning?
Daoguang Zan, Ailun Yu, Bo Shen +8
When human programmers have mastered a programming language, it would be easier when they learn a new programming language. In this report, we focus on exploring whether programmin…
Private-Library-Oriented Code Generation with Large Language Models
Daoguang Zan, Bei Chen, Yongshun Gong +6
Large language models (LLMs), such as Codex and GPT-4, have recently showcased their remarkable code generation abilities, facilitating a significant boost in coding efficiency. Th…
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
Bo Shen, Jiaxin Zhang, Taihong Chen +9
Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task.…