Search papers, labs, and topics across Lattice.
2
0
7
10
Agentic coding gets a serious boost: representing rollouts as structured summaries and then recursively comparing them lets Claude-4.5-Opus jump from 70.9% to 77.6% on SWE-Bench Verified.
Turn sparse binary rewards into dense supervision signals by having a model revise its own work, then distilling the revision strategy back into the original generation.
