From the 3 of 6 linked papers with an AI index.
6 papers
SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
Yihao Chen, Shi Chang, Feng Lin +4
The paper introduces SpecFirst, a two-stage framework that first elicits a behavioral specification from an execute-only binary and documentation before synthesizing code, improvin…
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
Yihao Chen, Shi Chang, Khaled Chawa +4
MindForge automatically turns open‑source command‑line programs into source‑free environments that expose only compiled executables and documentation, enabling the training of smal…
VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection
Yiheng Cao, Yihao Chen, Xin Hu +9
VulWeaver is an LLM‑driven system that improves source‑code vulnerability detection by combining deterministic static analysis with LLM‑based semantic inference to build a unified…
SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints
Zhiyu Fan, Kirill Vasilevski, Dayi Lin +6
The advancement of large language models (LLMs) and code agents has demonstrated significant potential to assist software engineering (SWE) tasks, such as autonomous issue resoluti…
SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation
Gustavo A. Oliva, Gopi Krishnan Rajbahadur, Aaditya Bhatia +7
High-quality labeled datasets are crucial for training and evaluating foundation models in software engineering, but creating them is often prohibitively expensive and labor-intens…
RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
Zhilong Chen, Chengzong Zhao, Boyuan Chen +9
Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present…