CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents Paper • 2611.01484 • Published 7 days ago • 26
"Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents Paper • 2610.40753 • Published 11 days ago • 16
Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup Paper • 2610.33129 • Published 17 days ago
HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference Paper • 2610.24611 • Published 23 days ago • 7
SWE-at-Scale: Scalable Issue Synthesis from Historical Bug Fixes Paper • 2610.21359 • Published 25 days ago • 20
Source Code Data Augmentation for Deep Learning: A Survey Paper • 2305.19915 • Published May 31, 2023 • 1
Executing as You Generate: Hiding Execution Latency in LLM Code Generation Paper • 2604.00491 • Published Apr 1 • 4
LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis Paper • 2601.05539 • Published Jan 9
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair Paper • 2606.26978 • Published Jun 25 • 2
RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue Paper • 2607.01213 • Published Jul 1 • 4
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents? Paper • 2607.01211 • Published Jul 1 • 12
How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study Paper • 2607.10856 • Published Jul 12 • 7
Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning Paper • 2503.14838 • Published Mar 19, 2025
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe Paper • 2608.13667 • Published Aug 13 • 18
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction Paper • 2609.02783 • Published Sep 2 • 55
The Embedder's Dilemma: LLMs Are Better, but at What Cost? Paper • 2608.12875 • Published Aug 13 • 12