I ran a quick experiment investigating how DeepSeek-R1 performs on agentic jobs, wiki.asexuality.org despite not supporting tool use natively, and I was rather amazed by preliminary results. This experiment runs DeepSeek-R1 in a single-agent setup, where the model not just prepares the actions however likewise formulates the actions as executable Python code. On a subset1 of the GAIA validation split, DeepSeek-R1 outshines Claude 3.5 Sonnet by 12.5% absolute, from 53.1% to 65.6% correct, and other models by an even bigger margin:

The experiment followed model use standards from the DeepSeek-R1 paper and the model card: Don't utilize few-shot examples, avoid adding a system prompt, and set the temperature to 0.5 - 0.7 (0.6 was used). You can discover more assessment details here.

Approach

DeepSeek-R1's strong coding abilities allow it to act as a representative without being clearly trained for tool use. By enabling the model to generate actions as Python code, it can flexibly communicate with environments through code execution.

Tools are implemented as Python code that is included in the timely. This can be a basic function meaning or a module of a bigger plan - any legitimate Python code. The model then creates code actions that call these tools.

Results from performing these actions feed back to the design as follow-up messages, driving the next steps until a final answer is reached. The representative structure is an easy iterative coding loop that mediates the discussion between the design and its environment.

Conversations

DeepSeek-R1 is used as chat model in my experiment, where the model autonomously pulls additional context from its environment by using tools e.g. by utilizing a search engine or bring information from websites. This drives the conversation with the environment that continues until a final response is reached.

On the other hand, o1 models are known to carry out poorly when used as chat models i.e. they do not attempt to pull context throughout a discussion. According to the connected article, o1 models perform best when they have the full context available, with clear directions on what to do with it.

Initially, I also attempted a complete context in a single prompt approach at each step (with arise from previous actions consisted of), however this led to significantly lower scores on the GAIA subset. Switching to the conversational technique explained above, I was able to reach the reported 65.6% performance.

This raises an intriguing question about the claim that o1 isn't a chat model - possibly this observation was more pertinent to older o1 models that lacked tool use capabilities? After all, isn't tool usage support an important system for making it possible for designs to pull extra context from their environment? This conversational technique certainly seems reliable for DeepSeek-R1, though I still require to conduct similar experiments with o1 designs.

Generalization

Although DeepSeek-R1 was mainly trained with RL on math and coding jobs, it is amazing that generalization to agentic jobs with tool usage through code actions works so well. This ability to generalize to agentic tasks reminds of recent research study by DeepMind that shows that RL generalizes whereas SFT remembers, although generalization to tool usage wasn't examined because work.

Despite its capability to generalize to tool use, DeepSeek-R1 frequently produces extremely long thinking traces at each action, compared to other designs in my experiments, limiting the effectiveness of this model in a single-agent setup. Even easier jobs often take a very long time to complete. Further RL on agentic tool use, be it via code actions or not, might be one alternative to enhance performance.

Underthinking

I also observed the underthinking phenomon with DeepSeek-R1. This is when a thinking design frequently switches between different reasoning thoughts without sufficiently exploring appealing paths to reach a proper service. This was a major factor for excessively long reasoning traces produced by DeepSeek-R1. This can be seen in the tape-recorded traces that are available for download.

Future experiments

Another typical application of thinking models is to use them for preparing only, while using other designs for creating code actions. This might be a prospective new feature of freeact, if this separation of functions shows useful for more complex jobs.

I'm also curious about how thinking designs that already support tool use (like o1, o3, ...) carry out in a single-agent setup, with and without generating code actions. Recent advancements like OpenAI's Deep Research or Hugging Face's open-source Deep Research, which likewise uses code actions, look fascinating.