Search papers, labs, and topics across Lattice.
5
0
6
15
AI agents can only correctly synthesize implementations and proofs for less than two-thirds of tested multi-module software repositories, revealing significant gaps in current capabilities.
LLMs can now automatically slim down and future-proof mathematical proofs, achieving 70% compression and 60% faster compilation by strategically rewriting them.
Turns out, you can bootstrap better formal specification synthesis by training on the iterative refinement trajectories of a traceable specification generator, leading to substantial gains in both specification accuracy and general reasoning.
LLMs can now be tested on their ability to formally verify real-world cryptographic assembly code, not just competition math problems.
Forget fixed decoding parameters: this RL-trained adapter dynamically adjusts LLM sampling strategies at inference, boosting accuracy by up to 10% under tight compute budgets.
