by JiayuJeff · Agent Tool · ★ 32
PlanBench-XL [Under Construction] This is the official repository for PlanBench-XL, a benchmark for evaluating LLM agents' long-horizon planning with massive tool ecosystems under retrieval noise and path-preserving blocker events. 🎯 Project Overview PlanBench-XL tests whether tool-use agents can solve retail planning tasks when they cannot see the whole tool universe at once. At each turn, the agent may retrieve relevant tools, call an available tool, or submit a final answer.
| Stars | 32 |
| Forks | 0 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 70.8288938573312/100 |
| Last Updated | 2026-06-28 |
| Created | 2026-06-20 |
| Platforms | python |
| Est. Tokens | ~15k |
Explore other popular agent tool tools:
PlanBench-XL is Official Repository for our paper: PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems. It is categorized as a Agent Tool with 32 GitHub stars.
PlanBench-XL is primarily written in Python. It covers topics such as agent, llm, long-horizon.
You can find installation instructions and usage details in the PlanBench-XL GitHub repository at github.com/JiayuJeff/PlanBench-XL. The project has 32 stars and 0 forks, indicating an active community.