117 citations · 414 across the 107 of their papers we have counts for
115 papers
MemScope: Evolving Agent Memory Architectures through Localized Code Repair
Miao Su, Yucan Guo, Zixuan Li +4
Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are typically fixed after deployment, limiting their adaptability across task typ…
Cavity-tunable Pseudospin-Hall Topology and Edge Transport
Minghui Niu, Yan Meng, Chengle Fan +5
Topological edge states are a hallmark of topological phases, with their existence tied to bulk band topology through bulk-edge correspondence. In photonic pseudospin-Hall systems,…
From Ranked Documents to Reliable Contexts: An Answer-Oriented Context Construct Framework for AI Search
Yunfei Zhong, Yinqiong Cai, Lixin Su +7
Traditional Web search follows a human-facing paradigm in which users inspect ranked documents and synthesize information themselves. In AI Search, retrieved documents instead serv…
RAdapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG
Yucan Guo, Miao Su, Saiping Guan +6
Retrieval-Augmented Generation (RAG) has become a prevailing paradigm for enhancing Large Language Models (LLMs) with non-parametric knowledge. Vanilla RAG efficiently handles simp…
HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning
Yucan Guo, Xiaohan Wang, Miao Su +8
Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has be…
DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving Repositories
Hongru Song, Ruqing Zhang, Jiafeng Guo +2
Recent advances in agentic large language models (LLMs) have enabled increasingly autonomous software engineering workflows, yet automatic machine learning (ML) paper-to-code repro…
ZenGen: Social Mind for LLMs
ZenGen Team, Ao Xiang, Bi Jingping +57
As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track…
Token-Flow Firewall: Semantic Runtime Auditing for Persistent AI Agents
Puji Wang, Yingchen Zhang, Ruqing Zhang +2
Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat assistants, unsafe content in thes…
EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer
Hao Zhang, Zhibin Zhang, Guangxin Wu +3
Large language models (LLMs) have achieved remarkable performance across diverse domains, yet their enormous computational and memory requirements hinder deployment in resource-con…
Detoxification for LLM: From Dataset Itself
Wei Shao, Yihang Wang, Gaoyu Zhu +4
Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself…
AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
Hongru Song, Yu-An Liu, Ruqing Zhang +4
Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack surfaces. We study knowledge-base…
Beyond Relevance: Utility-Centric Retrieval in the LLM Era
Hengran Zhang, Minghao Tang, Keping Bi +1
Information retrieval systems have traditionally optimized for topical relevance-the degree to which retrieved documents match a query. However, relevance only approximates a deepe…
Towards Knowledgeable Deep Research: Framework and Benchmark
Wenxuan Liu, Zixuan Li, Long Bai +13
Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive reports. In contrast to existing…
Relevance Supervision Can Teach Neural Retrievers to Prefer LLM-Generated Text
Wei Huang, Keping Bi, Yinqiong Cai +3
Recent studies show that neural retrievers often exhibit source bias, ranking LLM-generated passages above semantically similar human-written ones, which threatens the reliability…
HighlightBench: Benchmarking Markup-Driven Table Reasoning in Scientific Documents
Lexin Wang, Shenghua Liu, Yiwei Wang +5
Visual markups such as highlights, underlines, and bold text are common in table-centric documents. Although multimodal large language models (MLLMs) have made substantial progress…
PRISM-: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Yuyao Ge, Shenghua Liu, Yiwei Wang +5
Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steeri…
Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning
Jiahan Chen, Da Li, Hengran Zhang +6
Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classi…
Bagging-Based Model Merging for Robust General Text Embeddings
Hengran Zhang, Keping Bi, Jiafeng Guo +4
General-purpose text embedding models underpin a wide range of NLP and information retrieval applications, and are typically trained on large-scale multi-task corpora to encourage…
Training Dense Retrievers with Multiple Positive Passages
Benben Wang, Minghao Tang, Hengran Zhang +2
Modern knowledge-intensive systems, such as retrieval-augmented generation (RAG), rely on effective retrievers to establish the performance ceiling for downstream modules. However,…
Gated Differentiable Working Memory for Long-Context Language Modeling
Lingrui Mei, Shenghua Liu, Yiwei Wang +7
Long contexts challenge transformers: attention scores dilute across thousands of tokens, critical information is often lost in the middle, and models struggle to adapt to novel pa…
MI-PRUN: Optimize Large Language Model Pruning via Mutual Information
Hao Zhang, Zhibin Zhang, Guangxin Wu +3
Large Language Models (LLMs) have become indispensable across various domains, but this comes at the cost of substantial computational and memory resources. Model pruning addresses…
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
Miao Su, Yucan Guo, Zhongni Hou +8
Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail…
Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
Wenda Wei, Yu-An Liu, Ruqing Zhang +6
Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step…
RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
Yucan Guo, Miao Su, Saiping Guan +4
Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs), typically from unstructured texts and structured graphs. While recent pr…