by qiqihezh · Agent Tool · ★ 171
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla GRPO on τ-bench airline (50-task, multi-turn).
| Stars | 171 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 52.2894523196696/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-27 |
| Created | 2026-04-29 |
| Platforms | python |
| Est. Tokens | ~13k |
Looking for a agentic-grpo-longhorizon alternative? If you're comparing agentic-grpo-longhorizon with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A framework for agentic tool use training with reinforcement learning
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graph
ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs (OpenAI, Anthropic, Gemini
Building AI agent with hyperpocket tool in a flash
Explore other popular agent tool tools:
agentic-grpo-longhorizon is Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla GRPO on τ-bench airline (50-task, multi-turn).. It is categorized as a Agent Tool with 171 GitHub stars.
agentic-grpo-longhorizon is primarily written in Python. It covers topics such as agentic-ai, grpo, long-horizon.
You can find installation instructions and usage details in the agentic-grpo-longhorizon GitHub repository at github.com/qiqihezh/agentic-grpo-longhorizon. The project has 171 stars and 11 forks, indicating an active community.
The top alternatives to agentic-grpo-longhorizon on Agent Skills Hub include ToolBrain, Open-AgentRL, llm-rl-environments-lil-course. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.