by WxxShirley · AI 工具 · ★ 24
Agent-STAR This repository is the official implementation of our paper: Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe. We use TravelPlanner as a long-horizon tool-use testbed, where agents must iteratively call tools to satisfy multifaceted constraints, i.e., commonsense and hard constraints. We implement STAR [Data Synthesis → SFT → RL], a unified post-training pipeline that systematically studies the agentic RL design space across five axes: reward shaping, model scaling, data composition, algorithm selection, and environmental stability.
| Stars | 24 |
| Forks | 1 |
| Language | Python |
| Category | AI 工具 |
| Quality Score | 44.2/100 |
| Last Updated | 2026-05-12 |
| Created | 2026-03-21 |
| Platforms | python |
| Est. Tokens | ~51k |
These tools work well together with Agent-STAR for enhanced workflows:
Explore other popular ai 工具 tools:
Agent-STAR is Official implementation for paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe". It is categorized as a AI 工具 with 24 GitHub stars.
Agent-STAR is primarily written in Python. It covers topics such as agent, agentic-rl, reinforcement-learning.
You can find installation instructions and usage details in the Agent-STAR GitHub repository at github.com/WxxShirley/Agent-STAR. The project has 24 stars and 1 forks, indicating an active community.