I ran a fast experiment investigating how DeepSeek-R1 carries out on agentic tasks, regardless of not supporting tool usage natively, and ratemywifey.com I was quite satisfied by preliminary outcomes. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not only prepares the actions but likewise develops the actions as executable Python code. On a subset1 of the GAIA recognition split, sitiosecuador.com DeepSeek-R1 outperforms Claude 3.5 Sonnet by 12.5% outright, from 53.1% to 65.6% proper, and other models by an even bigger margin:

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

Approach

DeepSeek-R1's strong coding abilities enable it to serve as an agent without being explicitly trained for tool use. By enabling the design to produce actions as Python code, it can flexibly interact with environments through code execution.

Tools are carried out as Python code that is included straight in the timely. This can be an easy function definition or a module of a bigger bundle - any legitimate 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 steps till a final answer is reached. The agent structure is a simple iterative coding loop that mediates the conversation between the design and its environment.

Conversations

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

On the other hand, o1 models are understood to carry out inadequately when used as chat models i.e. they do not try to pull context during a discussion. According to the connected post, o1 models carry out best when they have the complete context available, with clear guidelines on what to do with it.

Initially, I likewise attempted a complete context in a single timely method at each step (with outcomes from previous steps consisted of), however this resulted in substantially lower scores on the GAIA subset. Switching to the explained above, I was able 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 did not have tool usage abilities? After all, isn't tool usage support an essential system for enabling designs to pull additional context from their environment? This conversational method certainly appears efficient for DeepSeek-R1, though I still need to perform similar experiments with o1 models.

Generalization

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

Despite its ability to generalize to tool use, DeepSeek-R1 frequently produces long reasoning traces at each action, compared to other models in my experiments, limiting the effectiveness of this design in a single-agent setup. Even simpler tasks in some cases take a long time to complete. Further RL on agentic tool use, be it through code actions or wiki.whenparked.com not, could be one choice to improve efficiency.

Underthinking

I also observed the underthinking phenomon with DeepSeek-R1. This is when a thinking design frequently switches in between various thinking thoughts without adequately exploring appealing paths to reach a proper solution. This was a significant reason for overly long thinking 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 designs is to utilize them for preparing just, while using other designs for producing code actions. This could be a potential new function of freeact, if this separation of roles proves helpful for more complex tasks.

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