messages stringlengths 4.24k 5.7k | split stringclasses 1
value |
|---|---|
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
[{"role": "system", "content": "## Tool-Use Protocol\n\n1. Reason inside <think>...</think> tags.\n2. Invoke one tool per turn using <tool_call> with JSON (keys: \"name\", \"arguments\").\n3. Environment returns results inside <tool_response>...</tool_response>.\n4. Reason again before the next action.\n5. When done or... | train |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.