arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.15089cs.AI
收藏

超越快速与缓慢:面向大语言模型的认知启发弹性推理

Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models

South China University of Technology(南方科技大学);Pazhou Laboratory(琶洲实验室);Peng Cheng Laboratory(鹏城实验室);Chongqing University of Posts and Telecommunications(重庆邮电大学)

Jinwu Hu, Dongjin Yang, Langyu Bian, Zhiquan Wen, Yufeng Wang, Yaofo Chen, Bin Xiao, Yuanqing Li, Mingkui Tan

AI总结:

本文提出CogER框架,通过动态选择推理策略提升大语言模型在不同难度查询中的推理效率与准确性。

摘要:

大型语言模型(LLMs)在各种语言任务中展现了出色的性能。然而,现有的LLM推理策略主要依赖于LLM本身,通过快速或缓慢模式(如o1思考)进行推理,因此在处理不同难度的查询时难以在推理效率和准确性之间取得平衡。在本文中,我们提出了受人类分层推理启发的弹性推理框架(CogER),该框架能够动态选择最适合每个查询的推理策略。具体而言,CogER首先评估输入查询的复杂性,并将其分配到几个预定义的级别之一,每个级别对应一种定制的处理策略,从而解决查询难度不可观测的问题。为了实现自动策略选择,我们将过程建模为马尔可夫决策过程,并使用强化学习训练CogER-Agent。该代理由一个平衡解的质量和计算成本的奖励函数引导,确保资源高效的推理。此外,对于需要外部工具的查询,我们引入了认知工具辅助推理,使LLM能够在其思维链中自主调用外部工具。广泛的实验表明,CogER在测试时间扩展方法上表现更优,在领域内任务中平均精确匹配度至少提高了13%,在领域外任务中提高了8%。

英文摘要:

Large language models (LLMs) have demonstrated impressive performance across various language tasks. However, existing LLM reasoning strategies mainly rely on the LLM itself with fast or slow mode (like o1 thinking) and thus struggle to balance reasoning efficiency and accuracy across queries of varying difficulties. In this paper, we propose Cognitive-Inspired Elastic Reasoning (CogER), a framework inspired by human hierarchical reasoning that dynamically selects the most suitable reasoning strategy for each query. Specifically, CogER first assesses the complexity of incoming queries and assigns them to one of several predefined levels, each corresponding to a tailored processing strategy, thereby addressing the challenge of unobservable query difficulty. To achieve automatic strategy selection, we model the process as a Markov Decision Process and train a CogER-Agent using reinforcement learning. The agent is guided by a reward function that balances solution quality and computational cost, ensuring resource-efficient reasoning. Moreover, for queries requiring external tools, we introduce Cognitive Tool-Assisted Reasoning, which enables the LLM to autonomously invoke external tools within its chain-of-thought. Extensive experiments demonstrate that CogER outperforms state-of-the-art Test-Time scaling methods, achieving at least a 13% relative improvement in average exact match on In-Domain tasks and an 8% relative gain on Out-of-Domain tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑