7 papers
Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay
Bingjie Li, Yumeng Song, Zhongming Yao +1
Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attribution cannot distinguish a jointl…
Robustness Analysis of Agentic AI to Inconsistent and Incomplete Tool Responses
Jiachen Xu, Torben Bach Pedersen, Zhongming Yao +2
Tool-using agents increasingly rely on external tools to complete multi-step tasks, but tool returns can fail in different ways and require different recovery actions. Existing rob…
VeriTS: Verifiable Model-Enhanced Time-Series Queries on Blockchain Systems
Zhongming Yao, Jun Pang, Chenxu Wang +3
Every blockchain transaction carries a timestamp, and the chain imposes a total order. On-chain data therefore forms per-source time-series streams. However, existing systems suppo…
A-CPES: A Reference Framework for Agentic AI in Cyber-Physical Energy Systems
Xiaoyu Zhang, Qiuye Sun, Jiachen Xu +2
Energy system operation contains a loop of work that automation has never taken over: posing the optimization problem the current cycle should solve, disposing of infeasibility, se…
VTRQ: Enabling Verifiable Trajectory Range Queries in Hybrid-Storage Blockchains
Zhongming Yao, Junchang Xin, Yumeng Song +7
Due to their increasingly large volumes, outsourcing of trajectory storage and querying to third-party service providers has become attractive. However, in such outsourced environm…
Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QA
Fengyu Li, Junhao Zhu, Kaishi Song +4
Table Question Answering (TQA) aims to answer natural language questions over structured tables. Large Language Models (LLMs) enable promising solutions to this problem, with opera…
TCRL: Temporal-Coupled Adversarial Training for Robust Constrained Reinforcement Learning in Worst-Case Scenarios
Wentao Xu, Zhongming Yao, Weihao Li +4
Constrained Reinforcement Learning (CRL) aims to optimize decision-making policies under constraint conditions, making it highly applicable to safety-critical domains such as auton…