29 citations · 77 across the 31 of their papers we have counts for
14 papers · 1 filter
A Viable Paradigm of Software Automation: Iterative End-to-End Automated Software Development
Jia Li, Zhi Jin, Huangzhao Zhang +3
Software development automation is a long-term goal in software engineering. With the development of artificial intelligence (AI), more and more researchers are exploring approache…
Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Yongding Tao, Tian Wang, Yihong Dong +4
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in train…
A Survey on Code Generation with LLM-based Agents
Yihong Dong, Xue Jiang, Jiaru Qian +4
Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm. Distinct from previous code generation techniques, code genera…
StackTrans: From Large Language Model to Large Pushdown Automata Model
Kechi Zhang, Ge Li, Jia Li +4
The Transformer architecture has emerged as a landmark advancement within the broad field of artificial intelligence, effectively catalyzing the advent of large language models (LL…
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…
Computational Thinking Reasoning in Large Language Models
Kechi Zhang, Ge Li, Jia Li +8
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as div…
SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
Huanyu Liu, Ge Li, Jia Li +3
How to design reinforcement learning (RL) tasks that effectively unleash the reasoning capability of large language models (LLMs) remains an open question. Existing RL tasks (e.g.,…
GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation
Jia Li, Xianjie Shi, Kechi Zhang +10
Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress for code generation. Recently, large…
SEAlign: Alignment Training for Software Engineering Agent
Kechi Zhang, Huangzhao Zhang, Ge Li +4
Recent advances in code generation models have demonstrated impressive capabilities in automating software development tasks, yet these models still struggle in real-world software…
LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding
Jia Li, Xuyuan Guo, Lei Li +7
Current advanced long-context language models offer great potential for real-world software engineering applications. However, progress in this critical domain remains hampered by…
aiXcoder-7B-v2: Training LLMs to Fully Utilize the Long Context in Repository-level Code Completion
Jia Li, Hao Zhu, Huanyu Liu +7
Large Language Models (LLMs) have shown promising results in repository-level code completion, which completes code based on the in-file and cross-file context of a repository. The…
Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
Yihong Dong, Ge Li, Xue Jiang +8
Periodicity, as one of the most important basic characteristics, lays the foundation for facilitating structured knowledge acquisition and systematic cognitive processes within hum…
Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points
Kechi Zhang, Ge Li, Jia Li +2
Code generation models have shown significant potential for automating programming tasks. However, the challenge of generating accurate and reliable code persists due to the highly…
Revisit Self-Debugging with Self-Generated Tests for Code Generation
Xiancai Chen, Zhengwei Tao, Kechi Zhang +7
Large language models (LLMs) have shown significant advancements in code generation, but still face challenges on tasks beyond their basic capabilities. Recently, the notion of sel…