4 papers
From Approval to Execution: Reconstruction-Aware Repair Analysis for LLM-Agent Software
Junchi Zhu, Zhenguang Liu, Shaojing Fan +2
Approval mechanisms have become a primary safeguard for consequential actions in LLM-agent software. Yet the action shown for approval is often not the object ultimately consumed:…
DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks
Rui Cao, Shaojing Fan, Liming Fang +3
Decentralized Finance (DeFi) has emerged as a rapidly growing blockchain-based financial service, where market transaction dynamics and underlying smart contract logic are intricat…
Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls
Guoyao Yu, Xiaoqing Sun, Ziqi Huang +13
Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool and orchestrating the order…
DeFiScreener: Efficient DeFi Attack Pre-screening in Smart Contracts via Historical Case Matching
Rui Cao, Shaojing Fan, Zhimei Sui +4
Blockchain and its killer applications, particularly decentralized finance (DeFi), are gaining widespread adoption, with over 5,200 DeFi projects deployed on mainstream blockchains…