作者位次 #3/12ACL 2026Findings· Findings of ACL
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
Ivan Rodkin · Daniil Orel · Konstantin Smirnov · Arman Bolatov · Bilal Elbouardi · Besher Hassan · Yuri Kuratov · Aydar Bulatov · Preslav Nakov · Timothy Baldwin · Artem Shelmanov · Mikhail Burtsev
摘要
Reasoning is a core capability of large language models (LLMs), yet how multi-step reasoning is learned and executed remains unclear. We study this question in a controlled cellular-automata (1dCA) framework that excludes memorization by using disjoint training and test rules. Given a short state...