External tools help large language models succeed at tasks where they would otherwise typically fail. In existing frameworks, choosing tools at test time relies on naive greedy decoding, regardless of whether the model has been fine-tuned on tool-annotated data or prompted with in-context examples. In contrast, we find that gathering and choosing among a suitable set of candidate tools has greater potential to lead to an optimal selection. We present Tool selECTion via meta-reasONing (TECTON), a two-phase system that first reasons over a task and outputs candidate tools using a custom fine-tuned language modelling head. Then, with the custom head disabled, it meta-reasons (i.e., it reasons over the previous reasoning process) to make a final choice. We show that TECTON results in substantial gains--both in-distribution and out-of-distribution--on a range of math reasoning datasets.
TInR: Exploring Tool-Internalized Reasoning in Large Language Models
The Hong Kong Polytechnic University(香港理工大学);Southeast University(东南大学);University of Edinburgh(爱丁堡大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
Southeast University(东南大学);King’s College London(伦敦国王学院);The Alan Turing Institute(艾伦·图灵研究所);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东科学院))
School of Computer Science and Technology, Beijing Institute of Technology, China(北京理工大学计算机科学与技术学院);School of Computer Science and Technology, Huazhong University of Science and Technology, China(华中科技大学计算机科学与技术学院);Independent, China(独立)
RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning
Wangxuan Institute of Computer Technology, Peking University(北京大学王萱计算机技术研究所);University of Chicago(芝加哥大学);University of California, Los Angeles(加州大学洛杉矶分校)
Searching Meta Reasoning Skeleton to Guide LLM Reasoning
Department of Electronic Engineering, Tsinghua University(清华大学电子工程系);Beijing Institute of Mathematical Sciences and Applications(北京数学科学与应用研究所);State Key laboratory of Space Network and Communications, Tsinghua University(清华大学空间网络与通信国家重点实验室)
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Tongji University(同济大学);Shanghai AI Laboratory(上海人工智能实验室);Nanyang Technological University(南洋理工大学);University of Science and Technology of China(中国科学技术大学);EPFL(苏黎世联邦理工学院);Wuhan University(武汉大学)
SciAgent: Tool-augmented Language Models for Scientific Reasoning
Microsoft(微软公司);University of California, Santa Barbara(加利福尼亚大学圣巴巴拉分校);Tsinghua University(清华大学);Singapore Management University(新加坡管理大学);Nanyang Technological University(南洋理工大学)
HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Meituan(美团)
Acting Less is Reasoning More! Teaching Model to Act Efficiently
The Chinese University of Hong Kong(香港中文大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴娜-香槟分校);Princeton University(普林斯顿大学);Sun Yat-sen University(中山大学);Hong Kong University of Science and Technology(香港科学理工大学)
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);School of Information, Renmin University of China(中国人民大学信息学院);Beijing Key Laboratory of Big Data Management and Analysis Methods(北京大数据管理与分析方法重点实验室)
ART: Automatic multi-step reasoning and tool-use for large language models
University of Washington(华盛顿大学);Microsoft Research(微软研究院);University of California, Irvine(加州大学欧文分校);Allen Institute of Artificial Intelligence(艾伦人工智能研究所);Meta AI
Interleaved Tool-Call Reasoning for Protein Function Understanding
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);Institute of Artificial Intelligence, Soochow University(苏州大学人工智能研究院);Changping Laboratory(昌平实验室);School of Software Engineering, USTC(中国科学技术大学软件学院)