1 citations · 2 across the 14 of their papers we have counts for
14 papers
LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory
Jing Yu, Yibo Zhao, Jiaming Zhang +1
Long-term memory enables LLM agents to leverage past interactions, but dialogue histories quickly exceed the context window, forcing agents to retrieve relevant subsets at query ti…
Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?
Qinnan Cai, Yibo Zhao, Xiang Li
Large language model based search agents increasingly adopt multi-agent architectures in which a main agent decomposes a complex question into sub-queries and dispatches them to pa…
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
Jianxiang Yu, Jiapeng Zhu, Bochen Lin +3
LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing ski…
Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?
Yibo Zhao, Zichen Ding, Jiayi Wu +2
Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid gro…
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Jiapeng Zhu, Jianxiang Yu, Yibo Zhao +5
Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divid…
Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG
Jiaming Zhang, Yibo Zhao, Jing Yu +2
GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question answering. However, existing…
TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews
Hanqi Duan, Xiang Li
LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured. Existing work e…
MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment
Zixuan Yang, Yibo Zhao, Weicong Liu +1
Matching submissions with suitable reviewers at scale is a growing challenge for major venues, yet existing approaches either rely on coarse proxy signals that conflate general rel…
APEX: Academic Poster Editing Agentic Expert
Chengxin Shi, Qinnan Cai, Zeyuan Chen +5
Designing academic posters is a labor-intensive process requiring the precise balance of high-density content and sophisticated layout. While existing paper-to-poster generation me…
GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence
Yibo Zhao, Jiapeng Zhu, Zichen Ding +1
Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs), yet systems remain susceptible to two critical flaws: providing correct…
Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization
Jing Yu, Yibo Zhao, Jiapeng Zhu +4
The widespread dissemination of toxic content on social media poses a serious threat to both online environments and public discourse, highlighting the urgent need for detoxificati…
Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
Yao Cheng, Yibo Zhao, Jiapeng Zhu +3
Large Language Models (LLMs) have demonstrated significant potential across various domains. However, they often struggle with integrating external knowledge and performing complex…
Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph
Yibo Zhao, Jiapeng Zhu, Can Xu +2
The rapid growth of social media platforms has raised significant concerns regarding online content toxicity. When Large Language Models (LLMs) are used for toxicity detection, two…
Improving Graph Out-of-distribution Generalization Beyond Causality
Can Xu, Yao Cheng, Jianxiang Yu +4
Existing methods for graph out-of-distribution (OOD) generalization primarily rely on empirical studies on synthetic datasets. Such approaches tend to overemphasize the causal rela…