Tag
A thought experiment questions whether instructing an AI model to never hallucinate would trigger self-reflection or result in the model gaslighting itself into believing it isn't hallucinating.
Introduces SAGE, the first end-to-end LLM-driven multi-agent framework for fraud detection, using a Data Diagnostic Tree and Markov decision process with natural-language gradients to optimize models under class imbalance. Experiments show significant F1 improvements over baselines across five datasets.
AlphaGRPO is a new framework that applies Group Relative Policy Optimization to Unified Multimodal Models, enhancing generation through self-reflective refinement and decompositional verifiable rewards.
GPT-Image-2 now has the ability to review its own generated outputs and iteratively refine them until satisfied with correctness, though this process can take around 11 minutes per image.