Agora, a consensus protocol debugging intelligent agent framework jointly built by 0G Lab, New National University, Peking University, and BUPT teams Odaily Planet Daily News: 0G Labs, together with research teams from the National University of Singapore, Peking University, and Beijing University of Posts and Telecommunications, proposed the first automated testing framework Agora in their ICML 2026 mid draft paper. This framework integrates domain knowledge with large model multi-agent collaboration, driving automated testing architecture through the interaction of three specialized agents: coordinators, strategists, and code officers. In the testing of consensus protocol libraries such as Raft, EPaxos, HotStuff, BullShark, Agora successfully discovered 15 previously unknown protocol level deep logic vulnerabilities. Compared to this, native large models such as GPT-5.2 and Claude 4.5 failed to detect vulnerabilities. The evaluation results show that the proportion of real logical vulnerabilities in Agora's vulnerability reports is 73.9%, with an average consumption of about 5.32 million tokens, equivalent to about $40, for each discovered logical vulnerability. At present, the framework code has been released in the open source community.