21 citations · 56 across the 26 of their papers we have counts for
28 papers
Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach
Jiarui Qin, Junjie Huang, Yunjia Xi +5
Agentic capabilities are increasingly important for modern LLMs, yet remain difficult to evaluate during pretraining. Existing approaches typically rely on static trajectory-derive…
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
Rong Shan, Te Gao, Hang Zheng +6
The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a critical structural vulnerabili…
Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
Yunjia Xi, Menghui Zhu, Jianghao Lin +4
Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most appr…
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Junru Lu, Jiarui Qin, Lingfeng Qiao +35
We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that r…
APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training
Jiarui Qin, Yunjia Xi, Junjie Huang +6
With the rapid development of LLM-based agents, there is a growing trend to incorporate agent-specific data into the pre-training stage of LLMs, aiming to better align LLMs with re…
Stop DDoS Attacking the Research Community with AI-Generated Survey Papers
Jianghao Lin, Rong Shan, Jiachen Zhu +3
Survey papers are foundational to the scholarly progress of research communities, offering structured overviews that guide both novices and experts across disciplines. However, the…
A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
Yunjia Xi, Jianghao Lin, Yongzhao Xiao +7
The advent of Large Language Models (LLMs) has significantly revolutionized web search. The emergence of LLM-based Search Agents marks a pivotal shift towards deeper, dynamic, auto…
Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
Jiachen Zhu, Menghui Zhu, Renting Rui +9
The advent of large language models (LLMs), such as GPT, Gemini, and DeepSeek, has significantly advanced natural language processing, giving rise to sophisticated chatbots capable…
Superplatforms Have to Attack AI Agents
Jianghao Lin, Jiachen Zhu, Zheli Zhou +4
Over the past decades, superplatforms, digital companies that integrate a vast range of third-party services and applications into a single, unified ecosystem, have built their for…
InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
Yunjia Xi, Jianghao Lin, Menghui Zhu +10
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding responses with retrieved information. As an emerging paradigm, Agentic RAG further enhances…
Position: The Real Barrier to LLM Agent Usability is Agentic ROI
Weiwen Liu, Jiarui Qin, Xu Huang +10
Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, plan…
Bursting Filter Bubble: Enhancing Serendipity Recommendations with Aligned Large Language Models
Yunjia Xi, Muyan Weng, Wen Chen +9
Recommender systems (RSs) often suffer from the feedback loop phenomenon, e.g., RSs are trained on data biased by their recommendations. This leads to the filter bubble effect that…
LIBER: Lifelong User Behavior Modeling Based on Large Language Models
Chenxu Zhu, Shigang Quan, Bo Chen +7
CTR prediction plays a vital role in recommender systems. Recently, large language models (LLMs) have been applied in recommender systems due to their emergence abilities. While le…
Beyond Positive History: Re-ranking with List-level Hybrid Feedback
Muyan Weng, Yunjia Xi, Weiwen Liu +5
As the last stage of recommender systems, re-ranking generates a re-ordered list that aligns with the user's preference. However, previous works generally focus on item-level posit…
A Survey on Diffusion Models for Recommender Systems
Jianghao Lin, Jiaqi Liu, Jiachen Zhu +5
While traditional recommendation techniques have made significant strides in the past decades, they still suffer from limited generalization performance caused by factors like inad…
Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models
Yunjia Xi, Weiwen Liu, Jianghao Lin +8
Recommender systems (RSs) play a pervasive role in today's online services, yet their closed-loop nature constrains their access to open-world knowledge. Recently, large language m…
Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding
Yunjia Xi, Hangyu Wang, Bo Chen +7
The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing depl…
MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models
Yunjia Xi, Weiwen Liu, Jianghao Lin +4
Conversational recommender systems (CRSs) aim to capture user preferences and provide personalized recommendations through multi-round natural language dialogues. However, most exi…
DisCo: Towards Harmonious Disentanglement and Collaboration between Tabular and Semantic Space for Recommendation
Kounianhua Du, Jizheng Chen, Jianghao Lin +6
Recommender systems play important roles in various applications such as e-commerce, social media, etc. Conventional recommendation methods usually model the collaborative signals…
Play to Your Strengths: Collaborative Intelligence of Conventional Recommender Models and Large Language Models
Yunjia Xi, Weiwen Liu, Jianghao Lin +5
The rise of large language models (LLMs) has opened new opportunities in Recommender Systems (RSs) by enhancing user behavior modeling and content understanding. However, current a…
ClickPrompt: CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction
Jianghao Lin, Bo Chen, Hangyu Wang +7
Click-through rate (CTR) prediction has become increasingly indispensable for various Internet applications. Traditional CTR models convert the multi-field categorical data into ID…
Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models
Yunjia Xi, Weiwen Liu, Jianghao Lin +8
Recommender systems play a vital role in various online services. However, the insulated nature of training and deploying separately within a specific domain limits their access to…
How Can Recommender Systems Benefit from Large Language Models: A Survey
Jianghao Lin, Xinyi Dai, Yunjia Xi +11
With the rapid development of online services, recommender systems (RS) have become increasingly indispensable for mitigating information overload. Despite remarkable progress, con…
A Bird's-eye View of Reranking: from List Level to Page Level
Yunjia Xi, Jianghao Lin, Weiwen Liu +5
Reranking, as the final stage of multi-stage recommender systems, refines the initial lists to maximize the total utility. With the development of multimedia and user interface des…