bodyandmindblog

I ran a quick experiment investigating how DeepSeek-R1 performs on agentic jobs, regardless of not supporting tool usage natively, and I was quite satisfied by initial results. This experiment runs DeepSeek-R1 in a single-agent setup, where the model not only prepares the actions however also develops the actions as executable Python code. On a subset1 of the GAIA validation split, DeepSeek-R1 exceeds Claude 3.5 Sonnet by 12.5% absolute, photorum.eclat-mauve.fr from 53.1% to 65.6% right, and other models by an even bigger margin:

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

Approach

DeepSeek-R1's strong coding abilities allow it to serve as an agent without being clearly trained for tool usage. By allowing the design to create actions as Python code, it can flexibly connect with environments through code execution.

Tools are carried out as Python code that is included 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 executing these actions feed back to the model as follow-up messages, driving the next steps till a last answer is reached. The representative structure is a simple iterative coding loop that mediates the conversation in between the model and its environment.

Conversations

DeepSeek-R1 is utilized as chat design in my experiment, where the model autonomously pulls extra context from its environment by using tools e.g. by utilizing a search engine or fetching data from web pages. This drives the discussion with the environment that continues up until a final answer is reached.

On the other hand, o1 models are known to perform poorly when utilized as chat models i.e. they don't try to pull context during a discussion. 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, online-learning-initiative.org I likewise attempted a full context in a single timely approach at each action (with results from previous actions included), however this caused substantially 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 a fascinating question about the claim that o1 isn't a chat design - perhaps this observation was more pertinent to older o1 designs that lacked tool use capabilities? After all, isn't tool use support an important mechanism for enabling designs to pull additional context from their environment? This conversational approach certainly appears reliable 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 jobs, it is remarkable that generalization to agentic jobs with tool usage 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 memorizes, although generalization to tool usage wasn't examined in that work.

Despite its ability to generalize to tool usage, DeepSeek-R1 typically produces really long reasoning traces at each step, compared to other models in my experiments, limiting the usefulness of this model in a single-agent setup. Even simpler tasks in some cases take a long time to finish. Further RL on agentic tool usage, be it via code actions or oke.zone not, could be one choice to enhance performance.

Underthinking

I also observed the underthinking phenomon with DeepSeek-R1. This is when a reasoning model regularly changes in between various thinking ideas without sufficiently exploring promising paths to reach a right . This was a significant reason for overly long thinking traces produced by DeepSeek-R1. This can be seen in the recorded traces that are available for download.

Future experiments

Another common application of thinking designs is to utilize them for planning just, while utilizing other designs for generating code actions. This could be a potential brand-new function of freeact, if this separation of functions proves useful for more complex tasks.

I'm also curious about how thinking designs that currently support tool use (like o1, o3, ...) carry out in a single-agent setup, with and wiki.whenparked.com without producing code actions. Recent developments like OpenAI's Deep Research or Hugging Face's open-source Deep Research, which likewise utilizes code actions, asteroidsathome.net look intriguing.