Mengkang Hu

Frontier LLMs can achieve substantial recursive self-improvement, closing nearly half of the performance gap on complex benchmarks by jointly optimizing data, training, and execution harnesses within a unified, agent-native environment.

Current multimodal agents can build sophisticated perception-control pipelines but fail to reliably execute physical tasks, losing object states and mistaking unfinished goals for completion.

Experimental results demonstrate the proposed $\mathcal{M}^2$Tok-based VLA achieves superior reconstruction fidelity but also significantly boosts the success rate of VLA models, and comprehensive ablation studies further confirm the effectiveness of the multi-head and multi-codebook mechanisms.

AI systems can now create and revise deliverables in ways that demand new standards for accountability and iterative improvement.

LLM agents can enhance training-data strategies in over half of their attempts, but their inconsistency reveals critical limitations in recursive self-improvement.