Search papers, labs, and topics across Lattice.
4
11
7
2
This work studies a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management, and finds that context management becomes increasingly valuable as the context-window budget tightens.
KD can significantly enhance model performance in low-data settings, but its effectiveness hinges on the quality of the teacher model.
Forget hand-crafted reward functions: CM2 uses checklists to train tool-using agents, outperforming SFT baselines by up to 12 points on key benchmarks.
Even the best LLMs fail more than 40% of the time when orchestrating multiple tools in realistic scenarios, revealing critical gaps in real-world agent capabilities.
