Search papers, labs, and topics across Lattice.
6
1
12
2
This work uses the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, and introduces the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement.
Argus achieves a 78% success rate on long-horizon reasoning tasks while using 21% fewer tokens in mature workflows, showcasing a revolutionary approach to agentic autonomy.
Despite high report quality, many models falter in citation accuracy and claim construction, exposing a disconnect between surface-level performance and deep reasoning skills.
UltraX achieves the highest average performance across datasets while using fewer training tokens, redefining efficiency in data refinement for LLMs.
A unified framework reveals that most optimizers only engage a fraction of their potential, providing a roadmap for more effective model training.
Forget bigger models: massive gains in document parsing accuracy are still possible through smarter data engineering alone.
