7 papers
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
Yihong Dong, Xue Jiang, Yongding Tao +11
Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). However, it struggles to break thro…
Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
Jie Cheng, Ruixi Qiao, Yingwei Ma +5
A significant aspiration of offline reinforcement learning (RL) is to develop a generalist agent with high capabilities from large and heterogeneous datasets. However, prior approa…
Large Language Model Unlearning for Source Code
Xue Jiang, Yihong Dong, Huangzhao Zhang +9
While Large Language Models (LLMs) excel at code generation, their inherent tendency toward verbatim memorization of training data introduces critical risks like copyright infringe…
Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format
Dingzirui Wang, Xuanliang Zhang, Rongyu Cao +8
Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning…
Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
Yingwei Ma, Yongbin Li, Yihong Dong +5
Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource…
Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
Yingwei Ma, Qingping Yang, Rongyu Cao +3
This paper presents Alibaba LingmaAgent, a novel Automated Software Engineering method designed to comprehensively understand and utilize whole software repositories for issue reso…