20 papers
Learning Reliable GUI Agents under Imperfect Priors
Bo Han, Qianyi Wang, Shuai Liu +9
GUI agents built on large language and vision-language models still struggle on unseen applications and complex multi-step tasks, as completing real GUI tasks depends on app-specif…
Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering
Yifan Wang, Xinkui Lin, Yongxiu Xu +9
Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely adopted for long-term conversation…
GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis
Long Zhang, Yuhan Chen, Chaoran Zhang +7
Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottlenecked by two fundamental is…
G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution
Shaoxiong Yang, Mengyuan Zhang, Shaojun Lin +4
Deep search has become a fundamental capability of large language models (LLMs) for solving open-domain complex tasks. However, existing approaches typically rely on linear sequent…
SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis
Zhuohang Fan, Beichen Zhang, Yuanfa Li +4
Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-covera…
ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis
Guohong Liu, Jialei Ye, Pengzhi Gao +4
GUI agents powered by large language models are advancing rapidly, creating urgent needs for evaluation and training based on realistic environments. However, directly doing so in…
Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
Heng Qu, Yike Liu, Renren Jin +4
Vision-Language Models (VLMs) have shown rapid progress in mobile GUI navigation. This paper presents a systematic study of data scaling, benchmarking, and reasoning for VLM-based…
InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward
Zhiwei Ning, Wenwen Tong, Xiangli Kong +12
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-cent…
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
Hybrid post-training combining supervised fine-tuning (SFT) and reinforcement learning (RL) is the standard paradigm for aligning large language models, yet fixed mixing schedules…
Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning
Wei Liu, Ting Long
Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain by leveraging data collected from a source domain. Existing works typically as…
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
Xiongbin Wu, Zhihao Luo, Shanzhe Lei +7
Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception…
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Aili Chen, Aonian Li, Baichuan Zhou +215
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
C-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models
Yue Yu, Ting Bai, HengZhi Lan +6
The attribution technique enhances the credibility of LLMs by adding citations to the generated sentences, enabling users to trace back to the original sources and verify the relia…
CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning
Yuxuan Liu, Weikai Xu, Kun Huang +9
Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, action decision and action funct…
FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
Shaoxiong Yang, Junting Li, Mengyuan Zhang +3
Small Language Models (SLMs) are attractive for cost-sensitive and resource-limited settings due to their efficient, low-latency inference. However, they often struggle with comple…
R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning
Zhizheng Jiang, Kang Zhao, Weikai Xu +5
Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise…
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…
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…
MobileViews: A Million-scale and Diverse Mobile GUI Dataset
Longxi Gao, Li Zhang, Shihe Wang +6
Visual language models (VLMs) empower mobile GUI agents to interpret complex mobile screens and respond to user requests. Training such capable agents requires large-scale, high-qu…