TravelPlanner benchmark (ICML 2024): OpenSymbolicAI achieves 100% pass rate with 6x fewer tokens than LangChain and 17x fewer LLM calls than CrewAI

ai-agents benchmark constraint-satisfaction llm multi-agent opensymbolicai python travel-planning
3 Open Issues Need Help Last updated: Mar 16, 2026

Open Issues Need Help

View All on GitHub

AI Summary: This GitHub issue aims to enhance the accessibility of the benchmark repository for new contributors. It proposes adding a concise quickstart guide to the README, standardizing the README's structure to align with other OpenSymbolicAI repos, and including a markdown table to summarize benchmark results by model and provider. The goal is to make it easier for newcomers to understand and run the benchmarks.

Complexity: 1/5
good first issue

TravelPlanner benchmark (ICML 2024): OpenSymbolicAI achieves 100% pass rate with 6x fewer tokens than LangChain and 17x fewer LLM calls than CrewAI

Python
#ai-agents#benchmark#constraint-satisfaction#llm#multi-agent#opensymbolicai#python#travel-planning
good first issue

TravelPlanner benchmark (ICML 2024): OpenSymbolicAI achieves 100% pass rate with 6x fewer tokens than LangChain and 17x fewer LLM calls than CrewAI

Python
#ai-agents#benchmark#constraint-satisfaction#llm#multi-agent#opensymbolicai#python#travel-planning

TravelPlanner benchmark (ICML 2024): OpenSymbolicAI achieves 100% pass rate with 6x fewer tokens than LangChain and 17x fewer LLM calls than CrewAI

Python
#ai-agents#benchmark#constraint-satisfaction#llm#multi-agent#opensymbolicai#python#travel-planning