11 papers
GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalation
Ruiyi Yang, Gayathri Lihinikaduarachchi, Rahat Masood +2
Privacy protection for live web traffic requires more than detecting private spans. Agent-based privacy protection systems must determine whether an outgoing action complies with t…
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
Ruiyi Yang, Lihuan Li, Hao Xue +1
Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A cent…
GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language
Jinwoong Kim, Rui Yang, Huishuai Zhang
We introduce GeoBuildBench, a benchmark designed to evaluate whether large language models and multimodal agents can ground informal natural-language plane geometry problems into e…
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
Runhui Huang, Jie Wu, Rui Yang +2
In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal…
TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding
Lihuan Li, Wilson Wongso, Baiyu Chen +6
Urban mobility is naturally expressed both as trajectories in space and as natural-language descriptions of travel intent, constraints, and preferences. However, prior work rarely…
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
Ruiyi Yang, Zechen Li, Hao Xue +2
Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iterati…
Orchard: An Open-Source Agentic Modeling Framework
Baolin Peng, Wenlin Yao, Qianhui Wu +11
Agentic modeling aims to transform LLMs into autonomous agents capable of solving complex tasks through planning, reasoning, tool use, and multi-turn interaction with external envi…
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
Fangyu Lei, Jinxiang Meng, Yiming Huang +14
Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into de…
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
Ruiyi Yang, Hao Xue, Imran Razzak +2
Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against latency and token/tool budgets. This paper…
Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
Ruiyi Yang, Hao Xue, Imran Razzak +3
Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy trade-offs when scaling to large kn…
SSTKG: Simple Spatio-Temporal Knowledge Graph for Intepretable and Versatile Dynamic Information Embedding
Ruiyi Yang, Flora D. Salim, Hao Xue
Knowledge graphs (KGs) have been increasingly employed for link prediction and recommendation using real-world datasets. However, the majority of current methods rely on static dat…