Search papers, labs, and topics across Lattice.
2
0
5
5
Query-conditioned reuse boosts agent success by 10.7 points while slashing token usage by nearly 50%, transforming how we leverage past experiences in AI tasks.
Even the most advanced LLMs like GPT-5.2 and Gemini-3 stumble on complex optimization problems, achieving only 27% accuracy on a new benchmark spanning stochastic, dynamic, and game optimization.
