List your company

Constraint Satisfaction Plan Generation on TravelPlanner

100Delivery RateReflexion
94.896.1597.598.85May 12, 2026

Evaluation results

MethodLinks
ReflexionLLM=Gemini-3.1-flash-lite2026.0510080.526.777.955.612.8
MIRRORLLM=GPT-4o2026.0510073.213.927.613.32.2
EvoAgentLLM=Gemini-2.5-Pro2026.0510078.123.957.940.612.2
PMCLLM=Gemini-2.5-Pro2026.0510078.730.643.337.223.3
ATLASLLM=Gemini-2.5-Pro2026.0510088.548.382.674.444.4
SDPLLM=Gemini-3.1-flash-lite2026.0510095.261.797.493.861.7
SDPLLM=GPT-4o2026.0510095.665.697.493.965.6
Plan-and-SolveLLM=Gemini-3.1-flash-lite2026.0599.484.726.178.956.713.3
GoalActLLM=Gemini-3.1-flash-lite2026.0599.483.12578.756.115
TDPLLM=Gemini-3.1-flash-lite2026.0599.481.627.279.261.113.3
ReActLLM=Gemini-3.1-flash-lite2026.059578.616.183.861.77.2