31 citations · 50 across the 51 of their papers we have counts for
19 papers · 1 filter
LightSearcher: Efficient DeepSearch via Experiential Memory
Hengzhi Lan, Yue Yu, Li Qian +5
DeepSearch paradigms have become a core enabler for deep reasoning models, allowing them to invoke external search tools to access up-to-date, domain-specific knowledge beyond para…
STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization
Yuhan Chen, Yuxuan Liu, Long Zhang +3
Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training…
ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning
Jinpeng Wang, Chao Li, Ting Ye +3
Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing…
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
Renren Jin, Pengzhi Gao, Yuqi Ren +6
Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, the ent…
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
Dingyu Yao, Chenxu Yang, Zhengyang Tong +4
The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usag…
GUI-PRA: Process Reward Agent for GUI Tasks
Tao Xiong, Xavier Hu, Yurun Chen +6
Long-horizon GUI automation remains challenging due to error accumulation over extended interaction sequences. Process Reward Models (PRMs) provide dense step-level supervision for…
Attention Basin: Why Contextual Position Matters in Large Language Models
Zihao Yi, Delong Zeng, Zhenqing Ling +6
The performance of Large Language Models (LLMs) is significantly sensitive to the contextual position of information in the input. To investigate the mechanism behind this position…
Mobile GUI Agents under Real-world Threats: Are We There Yet?
Guohong Liu, Jialei Ye, Jiacheng Liu +5
Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on n…
TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation
Renren Jin, Tianhao Shen, Xinwei Wu +9
Conducting supervised and preference fine-tuning of large language models (LLMs) requires high-quality datasets to improve their ability to follow instructions and align with human…
End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
Guanzhong Chen, Shaoxiong Yang, Chao Li +3
Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the difficulty of producing controllable…
BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism
Qinzhuo Wu, Pengzhi Gao, Wei Liu +1
Graphical User Interface (GUI) agents have gained substantial attention due to their impressive capabilities to complete tasks through multiple interactions within GUI environments…
TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization
Dingyu Yao, Bowen Shen, Zheng Lin +4
The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV…
GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning
Longxi Gao, Li Zhang, Pengzhi Gao +3
Training effective Vision-Language Models (VLMs) for GUI agents typically depends on large-scale annotated datasets, whose collection is both labor-intensive and error-prone. We in…
MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
Kun Huang, Weikai Xu, Yuxuan Liu +6
The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse…
Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents
Weikai Xu, Zhizheng Jiang, Yuxuan Liu +7
VLM-based mobile agents are increasingly popular due to their capabilities to interact with smartphone GUIs and XML-structured texts and to complete daily tasks. However, existing…
Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
Juntian Zhang, Chuanqi cheng, Yuhan Liu +3
Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable perfo…
MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions
Yuxuan Liu, Hongda Sun, Wei Liu +3
Mobile phone agents can assist people in automating daily tasks on their phones, which have emerged as a pivotal research spotlight. However, existing procedure-oriented agents str…
Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
Menglong Cui, Pengzhi Gao, Wei Liu +2
Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. I…
ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation
Qinzhuo Wu, Wei Liu, Jian Luan +1
Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solv…