Search papers, labs, and topics across Lattice.
7
0
11
4
OpenForgeRL reveals that decoupling training from inference can dramatically enhance the performance and reliability of AI agents in real-world applications.
TRACE transforms how long-horizon agents are trained, leading to a remarkable performance increase on complex tasks without the need for supervised fine-tuning.
OpenWebRL-4B sets a new benchmark for open-source visual web agents, achieving impressive success rates with minimal initial data while outperforming larger-scale competitors.
Recurrent memory can be added to transformers at scale with minimal parameter overhead and no performance penalty by reusing existing hidden states and training with interleaved parallel updates.
Forget toy tasks: scaling synthetic computer environments unlocks surprisingly effective training data for agents tackling month-long, real-world productivity workflows.
Autonomous web agents get a serious upgrade with WebXSkill, which lets them learn and execute skills with both code-level precision and human-readable guidance.
GUI agents can achieve significantly stronger task-solving capabilities through carefully designed post-training and data curation, without relying on costly online data collection.
