The current example in
https://python.langchain.com/en/latest/modules/agents/plan_and_execute.html
has inconsistent reasoning step (observing 28 years and thinking it's 26
years):
```
Observation: 28 years
Thought:Based on my search, Gigi Hadid's current age is 26 years old.
Action:
{
"action": "Final Answer",
"action_input": "Gigi Hadid's current age is 26 years old."
}
```
Guessing this is model noise. Rerunning seems to give correct answer of
28 years.
"Thought:\u001b[32;1m\u001b[1;3mBased on my search, Gigi Hadid's current age is 26 years old. \n",
"Thought:\u001b[32;1m\u001b[1;3mPrevious steps: steps=[(Step(value=\"Search for Leo DiCaprio's girlfriend on the internet.\"), StepResponse(response='Leo DiCaprio is currently linked to Gigi Hadid.')), (Step(value='Find her current age.'), StepResponse(response='28 years'))]\n",
"\n",
"Current objective: None\n",
"\n",
"Action:\n",
"```\n",
"{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"Gigi Hadid's current age is 26 years old.\"\n",
" \"action_input\": \"Gigi Hadid's current age is 28 years.\"\n",
"}\n",
"```\n",
"\n",
"\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
@ -209,64 +213,39 @@
"\n",
"Step: Find her current age.\n",
"\n",
"Response: Gigi Hadid's current age is 26 years old.\n",
"Response: Gigi Hadid's current age is 28 years.\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction:\n",
"```\n",
"{\n",
" \"action\": \"Calculator\",\n",
" \"action_input\": \"26 ** 0.43\"\n",
" \"action_input\": \"28 ** 0.43\"\n",
"}\n",
"```\n",
"\n",
"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",