14 citations · 67 across the 56 of their papers we have counts for
14 papers · 1 filter
WorldFailBench: Do World Models Understand Policy Failures?
Zheng Zhang, Xiaoyang Tang, Shuaiqi Cheng +11
Robot policy evaluation informs deployment decisions and policy improvement, but physical testing and simulator preparation require substantial effort. World models offer a complem…
CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing
Runang He, Tongya Zheng, Jing Cao +7
Pseudonymous accounts and complex smart-contract ecosystems substantially hinder the tracing of illicit cryptocurrency fund flows. Existing Graph Neural Networks (GNNs) have achiev…
Recall Begets Recall: Recurrent Memory Ranking for Personalized LLMs
Pengyue Jia, Shida Yan, Shunyu Liu +4
Memory ranking is the stage in personalized Large Language Models (LLMs) that decides which of the candidate memories returned by a retriever enter the limited context, so that the…
GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics
Weiqi Jiang, Yuchen Ying, Rui Wang +5
Graph agents extend large language models (LLMs) with the ability to actively explore and reason over knowledge graphs through multi-step interactions with graph tools. However, tr…
CodeTS: Verifiable Text-to-Time Series Generation via Executable Code
Xudong Yuan, Shunyu Liu, Tongya Zheng +3
Text-to-Time Series Generation (Text-to-TS) provides a promising paradigm for synthesizing time series from natural language, enabling scenario-specific generation when real observ…
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
Yang Zhou, Zixuan Huang, Sunzhu Li +10
Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that r…
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
Zetian Hu, Shunyu Liu, Junjie Zhang +4
Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on…
OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
Tianyi Lin, Chuanyu Sun, Jingyi Zhang +6
Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a framew…
STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
Junjie Zhang, Guozheng Ma, Shunyu Liu +5
Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level…
GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
Yuchen Ying, Weiqi Jiang, Tongya Zheng +4
Knowledge graphs provide structured and reliable information for many real-world applications, motivating increasing interest in combining large language models (LLMs) with graph-b…
R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?
Jingyi Zhang, Tianyi Lin, Huanjin Yao +3
In this work, we aim to develop effective data synthesis techniques that autonomously synthesize multimodal training data for enhancing MLLMs in solving complex real-world tasks. T…
Physics-informed Diffusion Generation for Geomagnetic Map Interpolation
Wenda Li, Tongya Zheng, Kaixuan Chen +8
Geomagnetic map interpolation aims to infer unobserved geomagnetic data at spatial points, yielding critical applications in navigation and resource exploration. However, existing…
VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning
Yibo Wang, Yongcheng Jing, Shunyu Liu +5
Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational co…
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation
Sunzhu Li, Jiale Zhao, Miteto Wei +6
Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation rem…