18 citations · 135 across the 104 of their papers we have counts for
35 papers · 1 filter
Laser: Governing Long-Horizon Agentic Search via Structured Protocol and Context Register
Shuting Wang, Qiaolin Xia, Vich Wang +3
Recent advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs) have enabled agentic search systems that interleave multi-step reasoning with external tool use. H…
GPG: Generalized Policy Gradient Theorem for Transformer-based Policies
Hangyu Mao, Guangting Dong, Zhicheng Dou
We present the Generalized Policy Gradient (GPG) Theorem, specifically designed for Transformer-based policies. Notably, we demonstrate that both standard Policy Gradient Theorem a…
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
Mengjie Deng, Guanting Dong, Zhicheng Dou
Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. Howeve…
Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation
Chenghao Zhang, Guanting Dong, Xinyu Yang +1
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) by retrieving relevant documents from an external corpus. However…
FinSight: Towards Real-World Financial Deep Research
Jiajie Jin, Yuyao Zhang, Yimeng Xu +3
Generating professional financial reports is a labor-intensive and intellectually demanding process that current AI systems struggle to fully automate. To address this challenge, w…
Agentic Entropy-Balanced Policy Optimization
Guanting Dong, Licheng Bao, Zhongyuan Wang +11
Recently, Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents. While mainstr…
DeepAgent: A General Reasoning Agent with Scalable Toolsets
Xiaoxi Li, Wenxiang Jiao, Jiarui Jin +8
Large reasoning models have demonstrated strong problem-solving abilities, yet real-world tasks often require external tools and long-horizon interactions. Existing agent framework…
MR-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval
Junjie Zhou, Ze Liu, Lei Xiong +10
Multimodal retrieval is becoming a crucial component of modern AI applications, yet its evaluation lags behind the demands of more realistic and challenging scenarios. Existing ben…
Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
Yifei Chen, Guanting Dong, Zhicheng Dou
Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools. However, models employing TIR often…
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao +6
Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deplo…
GLARE: Agentic Reasoning for Legal Judgment Prediction
Xinyu Yang, Chenlong Deng, Zhicheng Dou
Legal judgment prediction (LJP) has become increasingly important in the legal field. In this paper, we identify that existing large language models (LLMs) have significant problem…
Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration
Yifei Chen, Guanting Dong, Yutao Zhu +1
Retrieval-Augmented Generation (RAG) technology has been widely applied in recent years. However, despite the emergence of various RAG frameworks, a single RAG framework still cann…
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
Wenhan Liu, Xinyu Ma, Weiwei Sun +4
Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models (LRMs), many studies…
P3: Prompts Promote Prompting
Xinyu Zhang, Yuanquan Hu, Fangchao Liu +1
Current large language model (LLM) applications often employ multi-component prompts, comprising both system and user prompts, to guide model behaviors. While recent advancements h…
HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search
Jiajie Jin, Xiaoxi Li, Guanting Dong +5
Complex information needs in real-world search scenarios demand deep reasoning and knowledge synthesis across diverse sources, which traditional retrieval-augmented generation (RAG…
MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
Haonan Chen, Hong Liu, Yuping Luo +4
Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use o…
Measuring Human Involvement in AI-Generated Text: A Case Study on Academic Writing
Yuchen Guo, Zhicheng Dou, Huy H. Nguyen +3
Content creation has dramatically progressed with the rapid advancement of large language models like ChatGPT and Claude. While this progress has greatly enhanced various aspects o…
Generate, Not Recommend: Personalized Multimodal Content Generation
Jiongnan Liu, Zhicheng Dou, Ning Hu +1
To address the challenge of information overload from massive web contents, recommender systems are widely applied to retrieve and present personalized results for users. However,…
Respond Beyond Language: A Benchmark for Video Generation in Response to Realistic User Intents
Shuting Wang, Yunqi Liu, Zixin Yang +3
Querying generative AI models, e.g., large language models (LLMs), has become a prevalent method for information acquisition. However, existing query-answer datasets primarily focu…
DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes
Jiehan Cheng, Zhicheng Dou
We propose DailyQA, an automatically updated dynamic dataset that updates questions weekly and contains answers to questions on any given date. DailyQA utilizes daily updates from…
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Guanting Dong, Yifei Chen, Xiaoxi Li +7
Recently, large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL). However, leveraging the RL algorithm to empower eff…
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization
Yutao Zhu, Jiajie Jin, Hongjin Qian +3
Existing studies have optimized retrieval-augmented generation (RAG) across various sub-tasks, such as query understanding and retrieval refinement, but integrating these optimizat…
Hierarchical Document Refinement for Long-context Retrieval-augmented Generation
Jiajie Jin, Xiaoxi Li, Guanting Dong +6
Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To addres…
Defending against Indirect Prompt Injection by Instruction Detection
Tongyu Wen, Chenglong Wang, Xiyuan Yang +5
The integration of Large Language Models (LLMs) with external sources is becoming increasingly common, with Retrieval-Augmented Generation (RAG) being a prominent example. However,…