86 citations · 154 across the 84 of their papers we have counts for
90 papers
From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
Runze Li, Yukun Zhao, Can Xu +5
Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage and readability under a fixed…
SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations
Yu Wang, Yuchen Li, Rui Kong +11
Large language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing routers are effective in si…
DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows
Zechun Niu, Yukun Zhao, Jiaxin Zhang +12
Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically separate tasks by application or…
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
Jiazhen Jiang, Boxi Cao, Lingyong Yan +6
As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating…
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
Lingyong Yan, Can Xu, Yukun Zhao +13
Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, veri…
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents
Dongsheng Zhu, Xuchen Ma, Yucheng Shen +5
Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures. We introduce ToolMaze, a benchmark…
Measuring Maximum Activations in Open Large Language Models
Luxuan Chen, Han Tian, Xinran Chen +9
The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and m…
KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
Shuai Wang, Yinan Yu
Large Language Models (LLMs) exhibit strong abilities in natural language understanding and generation, yet they struggle with knowledge-intensive reasoning. Structured Knowledge G…
LLM-based Listwise Reranking under the Effect of Positional Bias
Jingfen Qiao, Jin Huang, Xinyu Ma +4
LLM-based listwise passage reranking has attracted attention for its effectiveness in ranking candidate passages. However, these models suffer from positional bias, where passages…
MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
Hui Wu, Haoquan Zhai, Yuchen Li +8
Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmente…
Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
Shuai Wang, Xixi Wang, Yinan Yu
Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios. Knowledge Base Question An…
How to Utilize Complementary Vision-Text Information for 2D Structure Understanding
Jiancheng Dong, Pengyue Jia, Derong Xu +9
LLMs typically linearize 2D tables into 1D sequences to fit their autoregressive architecture, which weakens row-column adjacency and other layout cues. In contrast, purely visual…
HATS: Hardness-Aware Trajectory Synthesis for GUI Agents
Rui Shao, Ruize Gao, Bin Xie +5
Graphical user interface (GUI) agents powered by large vision-language models (VLMs) have shown remarkable potential in automating digital tasks, highlighting the need for high-qua…
AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
Qiyang Li, Rui Kong, Yuchen Li +5
The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Mode…
Model Editing for New Document Integration in Generative Information Retrieval
Zhen Zhang, Zihan Wang, Xinyu Ma +6
Generative retrieval (GR) reformulates the Information Retrieval (IR) task as the generation of document identifiers (docIDs). Despite its promise, existing GR models exhibit poor…
DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
Tongzhou Wu, Yuhao Wang, Xinyu Ma +4
Deep-research agents are capable of executing multi-step web exploration, targeted retrieval, and sophisticated question answering. Despite their powerful capabilities, deep-resear…
Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment
Hui Wu, Hengyi Cai, Jinman Zhao +6
Offline preference optimization aligns reasoning models from fixed chosen--rejected pairs, yet standard methods apply gradient updates from every pair regardless of its training va…
MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
Changle Qu, Sunhao Dai, Hengyi Cai +3
Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing rei…
Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models
Can Xu, Lingyong Yan, Jiayi Wu +6
Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoni…
Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search
Yiqun Chen, Lingyong Yan, Zixuan Yang +5
Agentic search has emerged as a promising paradigm for complex information seeking by enabling Large Language Models (LLMs) to interleave reasoning with tool use. However, prevaili…
FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding
Yuchen Li, Rui Kong, Zhonghao Lyu +11
Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolut…
Reinforced Efficient Reasoning via Semantically Diverse Exploration
Ziqi Zhao, Zhaochun Ren, Jiahong Zou +9
Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensio…
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…
Learning a Single Token to Replace Long System Prompts in LLMs
Jiancheng Dong, Pengyue Jia, Jingyu Peng +7
Long system prompts are widely used to steer Large Language Models (LLMs), but repeatedly processing them at inference time is inefficient and consumes valuable context budget. Thi…