From 92aadef70732747fa6cc923ac038fd1c89661552 Mon Sep 17 00:00:00 2001
From: Aymeric Roucher <69208727+aymeric-roucher@users.noreply.github.com>
Date: Fri, 14 Feb 2025 13:12:10 +0100
Subject: [PATCH] Fix prompt for toolcalling agent and slightly update doc
 (#650)

---
 docs/source/en/conceptual_guides/react.md     | 7 -------
 src/smolagents/prompts/toolcalling_agent.yaml | 6 +++---
 2 files changed, 3 insertions(+), 10 deletions(-)

diff --git a/docs/source/en/conceptual_guides/react.md b/docs/source/en/conceptual_guides/react.md
index c2941a1..b86c438 100644
--- a/docs/source/en/conceptual_guides/react.md
+++ b/docs/source/en/conceptual_guides/react.md
@@ -38,11 +38,6 @@ For a `CodeAgent`, it looks like the figure below.
 
 <div class="flex justify-center">
     <img
-        class="block dark:hidden"
-        src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolagents/codeagent_docs.png"
-    />
-    <img
-        class="hidden dark:block"
         src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolagents/codeagent_docs.png"
     />
 </div>
@@ -60,8 +55,6 @@ Here is a video overview of how that works:
     />
 </div>
 
-![Framework of a React Agent](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/open-source-llms-as-agents/ReAct.png)
-
 We implement two versions of agents: 
 - [`CodeAgent`] is the preferred type of agent: it generates its tool calls as blobs of code.
 - [`ToolCallingAgent`] generates tool calls as a JSON in its output, as is commonly done in agentic frameworks. We incorporate this option because it can be useful in some narrow cases where you can do fine with only one tool call per step: for instance, for web browsing, you need to wait after each action on the page to monitor how the page changes.
diff --git a/src/smolagents/prompts/toolcalling_agent.yaml b/src/smolagents/prompts/toolcalling_agent.yaml
index 7489b9f..e033072 100644
--- a/src/smolagents/prompts/toolcalling_agent.yaml
+++ b/src/smolagents/prompts/toolcalling_agent.yaml
@@ -97,9 +97,9 @@ system_prompt: |-
   {%- endfor %}
 
   {%- if managed_agents and managed_agents.values() | list %}
-  You can also give requests to team members.
-  Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'request', a long string explaining your request.
-  Given that this team member is a real human, you should be very verbose in your request.
+  You can also give tasks to team members.
+  Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task', a long string explaining your task.
+  Given that this team member is a real human, you should be very verbose in your task.
   Here is a list of the team members that you can call:
   {%- for agent in managed_agents.values() %}
   - {{ agent.name }}: {{ agent.description }}