Agent-RL/ReCall
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
ReCall helps AI developers train Large Language Models (LLMs) to use a variety of external tools effectively, without needing extensive pre-labeled data. It takes an existing LLM and teaches it to reason with tools like search engines or custom functions, producing a more capable, agentic LLM. This is for AI engineers or researchers who want to enhance an LLM's ability to solve complex, multi-step tasks by integrating external functionalities.
1,343 stars. No commits in the last 6 months.
Use this if you need to train an LLM to dynamically call and combine various tools (like a web search, calculator, or custom API) to solve problems, especially when you lack specific supervised training data for tool use.
Not ideal if you're a business user looking for a pre-built AI agent or if you don't have the technical expertise to set up and manage LLM training environments, as this is a developer framework.
Stars
1,343
Forks
79
Language
Python
License
MIT
Category
Last pushed
May 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Agent-RL/ReCall"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
LLM360/Reasoning360
A repo for open research on building large reasoning models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models