BestHub
Sign in
JD Tech Talk
JD Tech Talk
Jan 9, 2026 · Artificial Intelligence

How JoyCode Agent Scored 74.6% Pass@1 on SWE‑bench Verified with a Patch‑Test Co‑generation Loop

JoyCode Agent leverages a patch‑test co‑generation and iterative validation framework to achieve a 74.6% Pass@1 score on the SWE‑bench Verified benchmark, reducing resource consumption by 30‑50% and introducing a closed‑loop multi‑agent pipeline that integrates testing, patch generation, trajectory compression, similarity retrieval, and decision arbitration.

AILLMMulti-agent
0 likes · 41 min read
How JoyCode Agent Scored 74.6% Pass@1 on SWE‑bench Verified with a Patch‑Test Co‑generation Loop
FunTester
FunTester
Aug 8, 2025 · Backend Development

How FixrLeak Uses Generative AI to Automatically Fix Java Resource Leaks

FixrLeak combines AST analysis with generative AI to detect and automatically repair Java resource leaks, dramatically reducing manual effort, improving code quality, and demonstrating the transformative potential of AI‑driven solutions in large‑scale software engineering.

ASTGenerative AIJava
0 likes · 9 min read
How FixrLeak Uses Generative AI to Automatically Fix Java Resource Leaks
Volcano Engine Developer Services
Volcano Engine Developer Services
Apr 14, 2025 · Artificial Intelligence

Introducing Multi‑SWE‑bench: The First Multilingual Code‑Fix Benchmark for LLMs

ByteDance’s Doubao model team has open‑sourced Multi‑SWE‑bench, a multilingual benchmark covering seven major programming languages with 1,632 real‑world bug‑fix tasks, complete Docker environments, difficulty grading, and strict human validation, aiming to evaluate and advance large‑language‑model code‑repair capabilities beyond Python.

LLM benchmarkcode repairdataset
0 likes · 11 min read
Introducing Multi‑SWE‑bench: The First Multilingual Code‑Fix Benchmark for LLMs