7 papers
OS-Bench: Evaluating SWE Agents on Cross-OS Code Migration
Qirui Jin, Kenan Li, Liao Zhu +8
Language-model (LM) agents are increasingly evaluated on repository-level software engineering (SWE) benchmarks derived from GitHub issues and pull requests. Although these benchma…
Multi-Agent System Search via Active Substructure-aware Policy Optimization
Beicheng Xu, Bowen Fan, Weitong Qian +2
LLMs enable multi-agent systems (MAS) to tackle complex tasks, but manually designing agent roles, prompts, and communication structures requires substantial expertise and effort.…
ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance
Qirui Jin, Lingching Tung, Kenan Li +12
Language model (LM) agents are increasingly deployed to maintain codebases over extended periods, fixing streams of related defects while carrying context from one fix to the next.…
Signature-Guided Capacity Occupancy for Dense Expert Merging
Lingching Tung, Chi-Jui Kim, Beicheng Xu +2
Dense expert merging combines domain-specialized language models into one single checkpoint, typically by admitting task-vector support in weight space. However, this admission is…
AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
Weitong Qian, Beicheng Xu, Zhongao Xie +16
Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review responses across long projec…
MFTune: An Efficient Multi-fidelity Framework for Spark SQL Configuration Tuning
Beicheng Xu, Lingching Tung, Yuchen Wang +2
Apache Spark SQL is a cornerstone of modern big data analytics.However,optimizing Spark SQL performance is challenging due to its vast configuration space and the prohibitive cost…
Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH
Beicheng Xu, Weitong Qian, Lingching Tung +2
To lower the expertise barrier in machine learning, the AutoML community has focused on the CASH problem, which jointly automates algorithm selection and hyperparameter tuning. Whi…