一作ACL 2026Poster· Natural Language Processing
r SIM : Incentivizing Reasoning Capabilities of LLM s via Reinforced Strategy Injection
Sijia Chen · Baochun Li · Di Niu
摘要
Large language models (LLMs) are post-trained through reinforcement learning (RL) to evolve into Reasoning Language Models (RLMs), where the hallmark of this advanced reasoning is “aha” moments when they start to perform strategies , such as self-reflection and deep thinking, within chain of thou...