Search papers, labs, and topics across Lattice.
2
0
6
2
Multi-iteration experience learning in LLMs can lead to capability collapse, but strategic adjustments in experience granularity and injection patterns can stabilize and enhance performance.
LLMs struggle with long-horizon reasoning in software engineering because they retrieve irrelevant memories, but aligning memory with subtasks boosts performance by 4.7 points on SWE-bench.
