I ran a quick experiment examining how DeepSeek-R1 carries out on agentic tasks, in spite of not supporting tool usage natively, and I was quite amazed by preliminary outcomes. This experiment runs DeepSeek-R1 in a single-agent setup, where the model not just prepares the actions but likewise formulates the actions as executable Python code. On a subset1 of the GAIA recognition split, DeepSeek-R1 exceeds Claude 3.5 Sonnet by 12.5% outright, from 53.1% to 65.6% correct, and other designs by an even bigger margin:

The experiment followed design usage guidelines from the DeepSeek-R1 paper and the design card: strikez.awardspace.info Don't utilize few-shot examples, avoid including a system timely, and set the temperature level to 0.5 - 0.7 (0.6 was used). You can find additional evaluation details here.

Approach

DeepSeek-R1's strong coding capabilities enable it to serve as an agent without being explicitly trained for tool use. By permitting the model to create actions as Python code, it can flexibly communicate with environments through code execution.

Tools are executed as Python code that is consisted of straight in the prompt. This can be a simple function definition or a module of a bigger package - any valid Python code. The design then creates code actions that call these tools.

Results from carrying out these actions feed back to the model as follow-up messages, driving the next actions up until a final answer is reached. The representative structure is a simple iterative coding loop that mediates the conversation in between the design and asteroidsathome.net its environment.

Conversations

DeepSeek-R1 is used as chat design in my experiment, where the design autonomously pulls extra context from its environment by using tools e.g. by using an online search engine or e.bike.free.fr bring data from web pages. This drives the conversation with the environment that continues till a final answer is reached.

In contrast, o1 designs are known to perform inadequately when used as chat models i.e. they don't attempt to pull context during a discussion. According to the linked short article, o1 designs perform best when they have the complete context available, with clear guidelines on what to do with it.

Initially, I likewise attempted a full context in a single timely technique at each action (with results from previous steps consisted of), however this resulted in considerably lower ratings on the GAIA subset. Switching to the conversational method explained above, I had the ability to reach the reported 65.6% efficiency.

This raises an interesting concern about the claim that o1 isn't a chat design - maybe this observation was more appropriate to older o1 designs that lacked tool usage abilities? After all, isn't tool usage support an important system for making it possible for models to pull extra context from their environment? This conversational technique certainly appears efficient for DeepSeek-R1, though I still require to perform comparable experiments with o1 models.

Generalization

Although DeepSeek-R1 was mainly trained with RL on mathematics and coding jobs, it is impressive that generalization to agentic jobs with tool use via code actions works so well. This capability to generalize to agentic tasks advises of recent research study by DeepMind that shows that RL generalizes whereas SFT remembers, oke.zone although generalization to tool usage wasn't examined because work.

Despite its capability to generalize to tool usage, DeepSeek-R1 often produces very long reasoning traces at each action, compared to other models in my experiments, restricting the effectiveness of this model in a single-agent setup. Even easier tasks often take a very long time to complete. Further RL on agentic tool use, wiki.whenparked.com be it by means of code actions or not, could be one choice to improve effectiveness.

Underthinking

I likewise observed the underthinking phenomon with DeepSeek-R1. This is when a thinking design regularly changes between different reasoning ideas without sufficiently checking out promising paths to reach a right service. This was a significant reason for extremely long thinking traces produced by DeepSeek-R1. This can be seen in the taped traces that are available for download.

Future experiments

Another typical application of reasoning models is to use them for preparing just, while using other designs for generating code actions. This might be a possible brand-new feature of freeact, if this separation of roles proves beneficial for more complex tasks.

I'm also curious about how thinking models that currently support tool usage (like o1, o3, ...) perform in a single-agent setup, with and without actions. Recent advancements like OpenAI's Deep Research or Hugging Face's open-source Deep Research, which also uses code actions, look intriguing.