Search papers, labs, and topics across Lattice.
3
0
5
3
RSIAgent is introduced, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction that substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.3.
LLMs may excel at predicting outcomes but often fail to grasp the underlying scientific validity of the laws they propose, revealing critical gaps in their discovery capabilities.
StructAgent transforms long-horizon task execution by ensuring that every progress update is grounded in verification, leading to dramatic improvements in success rates.
