Understand this story
The UC Santa Barbara paper proposes the TTME method, which replaces test-time training with evolutionary memory in mathematical discovery tasks: keeping model weights unchanged, it stores the rules and score-improvement ideas from previous attempts in memory to guide subsequent attempts. The report states that across 5 mathematical tasks, 2 frameworks, and 3 models, TTME exceeded the reported test-time training scores every time; on 3 tasks with Qwen3-8B, its FLOPs were reduced by 82.8% to 84.6%, and runtime was reduced by 47.7% to 58.4%. The authors suggest that if an LLM search loop comes with an automatic checker, one can first try using experiential memory rather than paying the cost of weight updates in the middle of the search. There are currently no further developments.
AI-generated from public reports
Developments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 29
Rohan Paul
UC Santa Barbara paper proposes TTME: replacing test-time training with evolutionary memory for mathematical discovery
A UC Santa Barbara paper proposes TTME, which replaces test-time training with evolutionary memory in mathematical discovery tasks, keeping weights unchanged and storing rules and score-improvement ideas from previous attempts in memory to guide subsequent attempts. Across 5 mathematical tasks, 2 frameworks, and 3 models, TTME exceeded the reported test-time training scores every time; on 3 tasks with Qwen3-8B, its FLOPs were reduced by 82.8% to 84.6%, and runtime was reduced by 47.7% to 58.4%. The authors suggest that if an LLM search loop comes with an automatic checker, one can first try using experiential memory rather than paying the cost of weight updates in the middle of the search.