2 citations · 7 across the 17 of their papers we have counts for
20 papers
Recall Begets Recall: Recurrent Memory Ranking for Personalized LLMs
Pengyue Jia, Shida Yan, Shunyu Liu +4
Memory ranking is the stage in personalized Large Language Models (LLMs) that decides which of the candidate memories returned by a retriever enter the limited context, so that the…
R-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search
Sheng Zhang, Junyi Li, Wenlin Zhang +6
Recent search agents for multi-hop reasoning often fail by either retrieving incomplete evidence or reasoning over irrelevant portions of the retrieved content, leading to a retrie…
Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization
Junyi Li, Xiaowei Qian, Yingyi Zhang +6
Recent advances in tool-integrated language agents have significantly improved their ability to solve complex reasoning tasks. However, existing alignment methods predominantly foc…
RAGR: Review-Augmented Generative Recommendation
Yingyi Zhang, Junyi Li, Yejing Wang +8
Sequential recommendation (SR) is traditionally formulated as next-item prediction over chronological item interactions. Although recent generative recommendation (GR) methods intr…
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
Sheng Zhang, Junyi Li, Yingyi Zhang +7
Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external kno…
Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
Xiaopeng Li, Wenlin Zhang, Yingyi Zhang +6
Deep Research agents driven by LLMs have automated the scholarly discovery pipeline, from planning and query formulation to iterative web exploration. Yet they remain constrained b…
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
Derong Xu, Shuochen Liu, Pengfei Luo +8
Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interacti…
From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space
Pengyue Jia, Xiaobei Wang, Yingyi Zhang +14
In modern recommender systems, list-wise reranking serves as a critical phase within the multi-stage pipeline, finalizing the exposed item sequence and directly impacting user sati…
GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization
Pengyue Jia, Derong Xu, Yingyi Zhang +5
Worldwide image geolocalization aims to predict precise GPS coordinates for images captured anywhere on Earth, which is challenging due to the large visual and geographic diversity…
Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
Yingyi Zhang, Junyi Li, Wenlin Zhang +8
Personalized large language models (LLMs) rely on memory retrieval to incorporate user-specific histories, preferences, and contexts. Existing approaches either overload the LLM by…
To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
Wenlin Zhang, Kuicai Dong, Junyi Li +9
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents…
Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation
Yue Que, Yingyi Zhang, Xiangyu Zhao +1
Graph-based recommender systems leverage neighborhood aggregation to generate node representations, which is highly sensitive to popularity bias, resulting in an echo effect during…
Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
Yingyi Zhang, Pengyue Jia, Derong Xu +9
Retrieval-Augmented Generation (RAG) critically depends on effective query expansion to retrieve relevant information. However, existing expansion methods adopt uniform strategies…
GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models
Pengyue Jia, Yingyi Zhang, Xiangyu Zhao +1
Geographic reasoning is a fundamental cognitive capability that requires models to infer plausible locations by synthesizing visual evidence with spatial world knowledge. Despite r…
Deep Research: A Survey of Autonomous Research Agents
Wenlin Zhang, Xiaopeng Li, Yingyi Zhang +5
The rapid advancement of large language models (LLMs) has driven the development of agentic systems capable of autonomously performing complex tasks. Despite their impressive capab…
From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
Derong Xu, Yi Wen, Pengyue Jia +8
Large Language Models (LLMs) have recently been widely adopted in conversational agents. However, the increasingly long interactions between users and agents accumulate extensive d…
Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation
Derong Xu, Pengyue Jia, Xiaopeng Li +9
Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks. Graph…
Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
Wenlin Zhang, Xiangyang Li, Kuicai Dong +9
Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However…
LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration
Yingyi Zhang, Pengyue Jia, Xianneng Li +8
Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user d…
A Survey of Personalization: From RAG to Agent
Xiaopeng Li, Pengyue Jia, Derong Xu +11
Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent r…