Tool learning with large language models: A survey

C Qu, S Dai, X Wei, H Cai, S Wang, D Yin, J Xu… - Frontiers of Computer …, 2025 - Springer
Recently, tool learning with large language models (LLMs) has emerged as a promising
paradigm for augmenting the capabilities of LLMs to tackle highly complex problems …

Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles

Q Chen, B Zhang, G Wang, Q Wu - arxiv preprint arxiv:2410.06733, 2024 - arxiv.org
While advancements in NLP have significantly improved the performance of Large
Language Models (LLMs) on tasks requiring vertical thinking, their lateral thinking …

CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance

Y Hao, P Cao, Z **, H Liao, Y Chen, K Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Tool learning enables the Large Language Models (LLMs) to interact with the external
environment by invoking tools, enriching the accuracy and capability scope of LLMs …

StepTool: A Step-grained Reinforcement Learning Framework for Tool Learning in LLMs

Y Yu, Z Wang, W Ma, Z Guo, J Zhan, S Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite having powerful reasoning and inference capabilities, Large Language Models
(LLMs) still need external tools to acquire real-time information retrieval or domain-specific …

InfCycle: Learning to Use Tools via Inference Compute and Cycle Consistency

J Li, W Wang, Y Chen, M Zhang - openreview.net
The scaling of inference-time computation in large language models (LLMs) has emerged
as a promising approach for enhancing reasoning capabilities by trading off inference-time …