Author

Xin Peng

h-index 5 View on Semantic Scholar

We have 3 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents

Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evide...

Bo-Yu Yang, Jia-Zheng Sun, Zi-Long Lu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents

Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by shallow trajectory retrieval and flat skill summarization, fundamentally ignoring the temporal dependencies and outcome-conditioned topology of agent behavior. We introdu...

Jia-Zheng Sun, Bo-Yu Yang, Bin-Hao Yuan et al. · 0 citations

Review Jul 2026

Traceable LLM Reasoning for Fake-Order Fraud Detection

Results show that DeepScrub improves fraud review accuracy, reduces first-stage review workload, and provides traceable evidence for production risk-review workflows, showing that domain adaptation can matter more than model scale in this setting.

Si-Qi You, Bingsong Xu, Zhixiang Zheng et al. · arXiv.org · 0 citations