5 papers
openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents
openJiuwen Team, Tao Yu, Xinyu Zhang +17
Long-horizon coding agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated agents, and multi-agent coordination. These t…
Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering
Xinyu Zhang, Zhicheng Dou, Deyang Li +10
As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify…
BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
Yuanhao Li, Hongbo Wang, Xiaotang Shang +3
Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR…
SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
Hongbo Wang, AprilPyone MaungMaung, Isao Echizen
Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understanding but inherit toxic signals from weakl…
DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs
Yuanhao Li, Mingshan Liu, Hongbo Wang +3
Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple…