Search papers, labs, and topics across Lattice.
6
0
8
11
Training on compound reasoning traces yields better generalization than isolated atomic modules, reshaping our understanding of how LLMs can learn to reason.
Claude Opus 4.6 outperforms its peers, solving over half of the complex tasks in a personalized desktop environment, revealing critical gaps in current AI capabilities.
iOSWorld reveals that even state-of-the-art models falter in multi-app reasoning, achieving only 37% accuracy, underscoring the complexity of personal context in AI interactions.
Today's best web agents are shockingly inefficient, achieving only 1.15% trajectory efficiency on realistic long-horizon tasks, revealing a critical need to move beyond simple success rates.
Agentic coding gets a serious boost: distilling and reusing rollout trajectories lets Claude-4.5-Opus jump from 70.9% to 77.6% on SWE-Bench Verified.
Forget simple scaling laws: the compute-optimal number of parallel rollouts in LLM RL plateaus, revealing distinct mechanisms for easy vs. hard problems.
