13 papers
LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery
Bo Yuan, Wenqian Ye, Zelin Zhao +4
Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from…
EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph
Zeyang Cui, Jiannong Cao, Zhiyuan Wen +3
Agent memory allows LLM agents to use earlier interactions when answering new queries. Existing methods often compress interaction histories into summaries or other LLM-generated r…
Automated Trajectory Evaluation for Mobile Agents via Step-Level Consequence Reasoning and Aggregation
Pengshuai Yang, Zijing Gao, Xue Yu +3
Evaluating language-guided mobile agents has recently shifted from rule-based to model-based approaches to achieve scalable and automated assessments. However, existing holistic ev…
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
Qu Tang, Benhui Zhuang, Bo Yuan +3
Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicitly model how physical scenes…
WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling
Zelin Zhao, Min Shi, Bo Yuan +5
World models aim to capture environment dynamics in ways that support perception, reasoning, and action, and have recently become a central direction in Vision-Language-Action-Worl…
SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction
Xue Yu, Bo Yuan, Kailin Zhao +3
Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks because a single errone…
PersonalPlan: Planning Multi-Agent Systems for Personalized Programming Learning
Zhiyuan Wen, Jiannong Cao, Peng Gao +4
Effective programming education requires personalized instruction adapted to diverse learner backgrounds. However, while LLM-based multi-agent systems (MAS) excel at complex planni…
FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaboration
Rui Cao, Jiannong Cao, Bo Yuan +2
Long-term action anticipation (LTA) aims to predict an ordered sequence of future verb-noun actions from a partially observed video. While this task serves as the foundation for em…
RMA: Context-Orchestrated Research Math Agents
Zelin Zhao, Bo Yuan, Yuchen Zhu +2
Long-horizon mathematical reasoning fails less often because a model cannot produce a valid next step than because an agent fails to maintain and expose the right semantic state ac…
FOCAL: Filtered On-device Continuous Activity Logging for Efficient Personal Desktop Summarization
Haoran Yin, Zhiyuan Wen, Jiannong Cao +2
Desktop interaction streams provide a continuous, privacy-sensitive record of interleaved user tasks. Transforming these streams into task-organized personal logs on-device faces t…
Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
Jaemoo Choi, Yuchen Zhu, Wei Guo +6
Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffu…
Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
Bo Yuan, Zelin Zhao, Petr Molodyk +2
Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural-language prompts. In practice, however, geomet…
Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
Yuchen Zhu, Wei Guo, Jaemoo Choi +4
Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinfor…