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.
Why read this
AI score 50
The original text provides comparison results of TTME across multiple tasks and models along with compute savings data, which can be used to judge whether a weight-update-free search approach is worth trying.
Topics
Body
New UC Santa Barbara paper shows that LLM math discovery can skip test-time training, since an evolving memory scored better and used far less compute.
i.e. evolving memory beats test-time training on math discovery, with far less compute.
Test-time training lets a model improve during a search by running RL on its own scored attempts. Those weight updates are slow and costly, so the method is hard to scale to bigger models.
They built TTME, which keeps the weights fixed and stores lessons in memory. The memory holds practical coding rules from earlier tries and the ideas behind score gains, which guide later attempts.
Across 5 math tasks, 2 frameworks, and 3 models, TTME beat the reported test-time training scores every time. With Qwen3-8B on 3 tasks, it used 82.8% to 84.6% fewer FLOPs and 47.7% to 58.4% less runtime than test-time training.
If your LLM search loop has an automatic checker, try a memory of lessons before paying for weight updates mid-search.