I ran a quick experiment examining how DeepSeek-R1 performs on agentic jobs, despite not supporting tool usage natively, and I was rather pleased by initial results. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not only plans the actions but also develops the actions as executable Python code. On a subset1 of the GAIA validation split, DeepSeek-R1 outperforms Claude 3.5 Sonnet by 12.5% absolute, from 53.1% to 65.6% right, and other designs by an even larger margin:

The experiment followed design usage guidelines from the DeepSeek-R1 paper and the model card: Don't utilize few-shot examples, avoid adding a system timely, and set the temperature level to 0.5 - 0.7 (0.6 was utilized). You can find further assessment details here.

Approach

DeepSeek-R1's strong coding abilities allow it to act as an agent without being explicitly trained for tool usage. By enabling the model to produce actions as Python code, it can flexibly connect with environments through code execution.

Tools are implemented as Python code that is included straight in the prompt. This can be an easy function definition or a module of a larger plan - any valid Python code. The design then produces code actions that call these tools.

Arise from carrying out these actions feed back to the model as follow-up messages, driving the next actions until a last answer is reached. The agent framework is an easy iterative coding loop that mediates the conversation in between the design and its environment.

Conversations

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

On the other hand, o1 designs are known to perform inadequately when used as chat designs i.e. they don't try to pull context throughout a conversation. According to the connected article, o1 designs carry out best when they have the complete context available, with clear directions on what to do with it.

Initially, I also tried a complete context in a single prompt technique at each step (with arise from previous steps included), but this resulted in considerably lower ratings on the GAIA subset. Switching to the conversational approach explained above, I had the ability to reach the reported 65.6% efficiency.

This raises a fascinating question about the claim that o1 isn't a chat model - possibly this observation was more relevant to older o1 designs that lacked tool use capabilities? After all, isn't tool use support a crucial mechanism for making it possible for designs to pull extra context from their environment? This conversational method certainly appears effective for DeepSeek-R1, though I still need to perform comparable try outs o1 designs.

Generalization

Although DeepSeek-R1 was mainly trained with RL on math and coding jobs, it is amazing that generalization to agentic tasks with tool use via code actions works so well. This ability to generalize to agentic jobs advises of current research by DeepMind that reveals that RL generalizes whereas SFT remembers, although generalization to tool use wasn't investigated in that work.

Despite its ability to generalize to tool use, wiki.insidertoday.org DeepSeek-R1 often produces long thinking traces at each step, compared to other designs in my experiments, restricting the usefulness of this model in a single-agent setup. Even easier tasks often take a long period of time to finish. Further RL on agentic tool usage, be it through code actions or not, could be one alternative to enhance effectiveness.

Underthinking

I likewise observed the underthinking phenomon with DeepSeek-R1. This is when a reasoning design often switches in between different thinking ideas without adequately exploring appealing courses to reach a proper 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 common application of thinking models is to utilize them for just, while utilizing other designs for generating code actions. This could be a possible new feature of freeact, if this separation of functions proves useful for more complex jobs.

I'm also curious about how reasoning models that already support tool usage (like o1, o3, ...) perform in a single-agent setup, with and without creating code actions. Recent developments like OpenAI's Deep Research or Hugging Face's open-source Deep Research, which likewise utilizes code actions, look interesting.