5 papers
AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills
Xinyuan Song, Zekun Cai, Liang Zhao
Designing an algorithm from a natural-language problem statement requires identifying the problem structure, reading constraints, choosing a suitable paradigm, checking correctness…
When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
Xinyuan Song, Zekun Cai, Liang Zhao
Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control. We study this risk in code LLMs, wh…
Manifold-Aware Temporal Domain Generalization for Large Language Models
Yiheng Yao, Zekun Cai, Xinyuan Song +4
Temporal distribution shifts are pervasive in real-world deployments of Large Language Models (LLMs), where data evolves continuously over time. While Temporal Domain Generalizatio…
Learning to Recommend Multi-Agent Subgraphs from Calling Trees
Xinyuan Song, Liang Zhao
Multi-agent systems (MAS) increasingly solve complex tasks by orchestrating agents and tools selected from rapidly growing marketplaces. As these marketplaces expand, many candidat…
StructPrune: Structured Global Pruning asymptotics with GPU Memory
Xinyuan Song, Guangji Bai, Liang Zhao
Pruning is critical for scaling large language models (LLMs). Global pruning achieves strong performance but requires memory, which is infeasible for billion-param…