Can Computation from Earlier Problems Help LLMs Solve New Ones?

Excerpt

arXiv:2609.39394v1 Announce Type: cross Abstract: Large language models often solve independent problems in the same conversation. Can computation from earlier problems help them solve new ones? To answer this question, we first conduct preliminary experiments showing that retained history can raise or lower later-turn accuracy, even within the same domain. To understand these effects, we use controlled replay to isolate internal state changes specific to each problem-history pairing. Across dif