3 citations · 3 across the 11 of their papers we have counts for
13 papers
When History Lies: Evaluating and Improving Tool Use under Misleading Multi-Turn Histories
Xiaoqing Wu, Xingyu Fan, Feifei Li +1
Tool-calling agents infer task state from accumulated dialogue and tool traces. In persistent interactions, however, historical traces may remain structurally valid and semanticall…
DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance
Zihan Li, Feifei Li, Wenhui Que
Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant. Conventiona…
WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback
Haoliang Ming, Feifei Li, Wenhui Que
Knowledge-base construction and querying are typically optimized in isolation: retrieval-augmented agents operate over a fixed, externally maintained index, whereas construction re…
WikiKV: Schema-Evolving Path-Indexed Storage for Hierarchical Knowledge Navigation
Feifei Li, Haoliang Ming, Zihan Li +5
LLM-curated hierarchical knowledge bases, namely a tree-structured wiki whose nodes summarize an underlying corpus, have become a dominant substrate for retrieval-augmented applica…
MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
Zihan Li, Xingyu Fan, Feifei Li +1
Existing agent memory systems universally follow what we term a Memory-as-Tool paradigm where a single query triggers one-shot retrieval of flat passage lists, suffering from passi…
Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
Haoliang Ming, Feifei Li, Xiaoqing Wu +1
LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when evidence is sufficient. Yet cu…
AuthTrace: Diagnosing Evidence Construction in Thematically Dense Single-Author Corpora
Xiaoqing Wu, Feifei Li, Haoliang Ming +1
Evidence construction--the stage that determines which passages reach the language model before generation begins--is evaluated paradigm by paradigm, leaving practitioners with no…
Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses
Kerui Peng, Feifei Li, Xingyu Fan +1
When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a failure we term Cross-Style Collapse. We…
HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistants
Hailong Li, Feifei Li, Wenhui Que +1
Large language models (LLMs) power many interactive systems such as chatbots, customer-service agents, and personal assistants. In knowledge-intensive scenarios requiring user-spec…
One Agent to Serve All: a Lite-Adaptive Stylized AI Assistant for Millions of Multi-Style Official Accounts
Xingyu Fan, Feifei Li, Wenhui Que +1
Conversational agents deployed in industrial-scale official account platforms must generate responses that are both contextually grounded and stylistically aligned-requirements tha…
Efficient Graph Embedding at Scale: Optimizing CPU-GPU-SSD Integration
Zhonggen Li, Xiangyu Ke, Yifan Zhu +2
Graph embeddings map graph nodes to continuous vectors and are foundational to community detection, recommendation, and many scientific applications. At billion-scale, however, exi…
CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG
Ziting Wang, Haitao Yuan, Wei Dong +2
Large Language Models (LLMs) have demonstrated impressive ability in generation and reasoning tasks but struggle with handling up-to-date knowledge, leading to inaccuracies or hall…
Optimal Matrix Sketching over Sliding Windows
Hanyan Yin, Dongxie Wen, Jiajun Li +4
Matrix sketching, aimed at approximating a matrix consisting of vector streams of length with a smaller sketching matrix $\boldsymbo…