Search papers, labs, and topics across Lattice.
Hubei Key Laboratory of Distributed System Security
5
0
8
13
LogicHunter uncovers 40 hidden bugs in LLM agent frameworks that traditional testing methods missed, achieving a groundbreaking 91.17% precision in bug detection.
A staggering 28% of mid-sized models' answers are mere spurious guesses, exposing critical flaws in their reasoning capabilities.
Completing incomplete ECGs can restore diagnostic performance to near-complete levels, unlocking the potential of vast clinical archives for AI applications.
Infinite Agentic Loops can turn a single request into a costly, endless cycle of execution, but IAL-Scan can detect and prevent these failures before they escalate.
AgentFlow reveals 238 critical prompt-to-tool risks in real-world agent programs, highlighting the hidden complexities of agent dependencies that traditional analysis tools miss.
