I ran a quick experiment examining how DeepSeek-R1 carries out on agentic tasks, regardless of not supporting tool usage natively, and I was rather satisfied by preliminary results. This experiment runs DeepSeek-R1 in a single-agent setup, where the model not just prepares the actions but also develops the actions as executable Python code. On a subset1 of the GAIA recognition split, DeepSeek-R1 outshines 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 model use guidelines from the DeepSeek-R1 paper and the design card: Don't use few-shot examples, avoid adding a system prompt, and set the temperature to 0.5 - 0.7 (0.6 was used). You can find more assessment details here.

Approach

DeepSeek-R1's strong coding abilities allow it to act as a representative without being explicitly trained for tool usage. By permitting the model to create actions as Python code, it can flexibly interact with environments through code execution.

Tools are executed as Python code that is consisted of straight in the timely. This can be a basic function meaning or a module of a larger package - any legitimate Python code. The model then generates 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 until a final response is . The representative framework is a basic iterative coding loop that mediates the conversation in between the model and its environment.

Conversations

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

On the other hand, o1 designs are understood to carry out poorly when used as chat designs i.e. they do not attempt to pull context during a conversation. According to the connected post, o1 models perform best when they have the full context available, with clear guidelines on what to do with it.

Initially, I likewise tried a full context in a single prompt approach at each action (with results from previous actions consisted of), but this caused significantly lower ratings on the GAIA subset. Switching to the conversational method explained above, I had the ability to reach the reported 65.6% performance.

This raises an intriguing concern about the claim that o1 isn't a chat design - maybe this observation was more appropriate to older o1 designs that did not have tool usage abilities? After all, isn't tool usage support a crucial system for enabling models to pull extra context from their environment? This conversational technique certainly appears reliable for photorum.eclat-mauve.fr DeepSeek-R1, though I still require to perform comparable try outs o1 designs.

Generalization

Although DeepSeek-R1 was mainly trained with RL on math and coding tasks, it is amazing that generalization to agentic jobs with tool use via 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 memorizes, although generalization to tool usage wasn't investigated because work.

Despite its capability to generalize to tool use, DeepSeek-R1 often produces extremely long thinking traces at each action, compared to other models in my experiments, limiting the usefulness of this design in a single-agent setup. Even simpler jobs in some cases take a long time to finish. Further RL on agentic tool usage, be it via code actions or not, could be one alternative to enhance performance.

Underthinking

I also observed the underthinking phenomon with DeepSeek-R1. This is when a thinking design regularly changes in between various thinking thoughts without adequately checking out appealing courses to reach an appropriate service. This was a major reason for excessively 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 reasoning designs is to utilize them for preparing only, while using other models for generating code actions. This might be a possible brand-new function of freeact, if this separation of roles shows helpful 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 generating code actions. Recent developments like OpenAI's Deep Research or Hugging Face's open-source Deep Research, which likewise uses code actions, look fascinating.