by Agent-RL · Agent Tool · ★ 1.3k
ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning We introduce ReCall, a novel framework that trains LLMs to Reason with Tool Call via reinforcement learning—without requiring any supervised data on tool use trajectories or reasoning steps. ReCall empowers LLMs to agentically use and combine arbitrary tools like OpenAI o3, offering an accessible approach toward general-purpose agents.
| Stars | 1,339 |
| Forks | 79 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 65.732589885484/100 |
| Open Issues | 30 |
| Last Updated | 2025-05-16 |
| Created | 2025-03-03 |
| Platforms | python |
| Est. Tokens | ~267k |
These tools work well together with ReCall for enhanced workflows:
Explore other popular agent tool tools:
ReCall is ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning. It is categorized as a Agent Tool with 1.3k GitHub stars.
ReCall is primarily written in Python. It covers topics such as agent, function-calling, llm.
You can find installation instructions and usage details in the ReCall GitHub repository at github.com/Agent-RL/ReCall. The project has 1.3k stars and 79 forks, indicating an active community.
ReCall is released under the MIT license, making it free to use and modify according to the license terms.