1 citations · 5 across the 14 of their papers we have counts for
17 papers
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
Boyu Yang, Jiazheng Sun, Zilong Lu +3
Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval…
Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents
Jiazheng Sun, Boyu Yang, Binhao Yuan +2
Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by shallow trajectory retrieval a…
Traceable LLM Reasoning for Fake-Order Fraud Detection
Siqi You, Bingsong Xu, Zhixian Zheng +4
Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features,…
CI4A: Semantic Component Interfaces for Agents Empowering Web Automation
Zhi Qiu, Jiazheng Sun, Chenxiao Xia +2
While Large Language Models demonstrate remarkable proficiency in high-level semantic planning, they remain limited in handling fine-grained, low-level web component manipulations.…
Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study
Mingwei Liu, Zheng Pei, Yanlin Wang +5
In low-resource framework development (e.g., HarmonyOS), large language models (LLMs) often lack sufficient pre-training exposure, resulting in poor code generation performance. Al…
Generating High-Quality Datasets for Code Editing via Open-Source Language Models
Zekai Zhang, Mingwei Liu, Zhenxi Chen +7
Code editing plays a vital role in software engineering, requiring developers to adjust existing code according to natural language instructions while keeping functionality intact…
ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling
Jianghao Lin, Yuanyuan Shi, Xin Peng +10
Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an inference-scaling framework for st…
EvolMathEval: Towards Evolvable Benchmarks for Mathematical Reasoning via Evolutionary Testing
Shengbo Wang, Mingwei Liu, Zike Li +4
The rapid advancement of Large Language Models (LLMs) poses a significant challenge to existing mathematical reasoning benchmarks. However, these benchmarks tend to become easier o…
A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback
Guoliang Duan, Mingwei Liu, Yanlin Wang +3
Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remai…
AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
Kaifeng He, Mingwei Liu, Chong Wang +4
Code generation with large language models (LLMs) is highly sensitive to token selection during decoding, particularly at uncertain decision points that influence program logic. Wh…
Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation
Mingwei Liu, Juntao Li, Ying Wang +9
Despite recent advances in Large Language Models (LLMs) for code generation, the quality of LLM-generated code still faces significant challenges. One significant issue is code rep…
FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks
Dekun Dai, MingWei Liu, Anji Li +5
Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated c…
RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation
Linxi Liang, Jing Gong, Mingwei Liu +5
Large Language Models (LLMs) have become pivotal tools for automating code generation in software development. However, these models face significant challenges in producing versio…
A Preliminary Study on the Robustness of Code Generation by Large Language Models
Zike Li, Mingwei Liu, Anji Li +4
Robustness is a critical factor for reliable code generation by large language models, yet most evaluations focus on correctness and overlook key issues such as missing input valid…
Evolving Triple Knowledge-Augmented LLMs for Code Translation in Repository Context
Guangsheng Ou, Mingwei Liu, Yuxuan Chen +5
Large language models (LLMs) have behaved well in function-level code translation without repository-level context. However, the performance of LLMs in repository-level context cod…
RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust
Guangsheng Ou, Mingwei Liu, Yuxuan Chen +3
Recent advancements in large language models (LLMs) have demonstrated impressive capabilities in code translation, typically evaluated using benchmarks like CodeTransOcean and Repo…
Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation
Tong Su, Xin Peng, Sarubi Thillainathan +3
Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability…