GitLab

I ran a quick experiment examining how DeepSeek-R1 carries out on agentic jobs, despite not supporting tool usage natively, and I was rather satisfied by preliminary outcomes. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not just prepares the actions however also formulates 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% proper, and other designs by an even larger margin:

The experiment followed model use standards from the DeepSeek-R1 paper and the model card: Don't use few-shot examples, prevent adding a system timely, and set the temperature level to 0.5 - 0.7 (0.6 was utilized). You can find further 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 allowing the model to create actions as Python code, it can flexibly engage with environments through code execution.

Tools are carried out as Python code that is consisted of straight in the prompt. This can be an easy function definition or a module of a bigger package - any legitimate Python code. The design then produces code actions that call these tools.

Results from carrying out these actions feed back to the design as follow-up messages, driving the next steps up until a final answer is reached. The agent framework is a simple iterative coding loop that mediates the discussion between the model 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 utilizing an online search engine or bring data from web pages. This drives the discussion with the environment that continues till a last response is reached.

In contrast, o1 models are known to carry out badly when utilized as chat models i.e. they do not attempt to pull context throughout a discussion. According to the linked short article, o1 designs carry out best when they have the full context available, with clear directions on what to do with it.

Initially, setiathome.berkeley.edu I also attempted a complete context in a single timely at each action (with arise from previous steps consisted of), however this resulted in considerably lower scores on the GAIA subset. Switching to the conversational method explained above, wiki.snooze-hotelsoftware.de I had the ability to reach the reported 65.6% performance.

This raises an intriguing question about the claim that o1 isn't a chat design - maybe this observation was more pertinent to older o1 designs that lacked tool usage abilities? After all, isn't tool use support a crucial system for sitiosecuador.com making it possible for models to pull additional context from their environment? This conversational technique certainly appears effective for DeepSeek-R1, oke.zone though I still need to carry out similar experiments with o1 designs.

Generalization

Although DeepSeek-R1 was mainly trained with RL on math and coding jobs, it is remarkable that generalization to agentic tasks with tool use by means of code actions works so well. This capability to generalize to agentic jobs advises of current research study by DeepMind that reveals that RL generalizes whereas SFT memorizes, setiathome.berkeley.edu although generalization to tool use wasn't examined because work.

Despite its capability to generalize to tool use, DeepSeek-R1 typically produces very 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 sometimes take a long period of time to finish. Further RL on agentic tool use, be it via code actions or not, could be one choice to improve effectiveness.

Underthinking

I also observed the underthinking phenomon with DeepSeek-R1. This is when a thinking design frequently changes in between various thinking ideas without adequately checking out promising courses to reach a proper service. This was a significant reason 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 designs is to use them for planning only, while utilizing other models for generating code actions. This could be a prospective new feature of freeact, oke.zone if this separation of functions shows useful for more complex jobs.

I'm also curious about how thinking models that already support tool use (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 uses code actions, look interesting.