GitLab

I ran a quick experiment investigating how DeepSeek-R1 carries out on agentic tasks, in spite of not supporting tool use natively, and I was rather pleased by preliminary results. This experiment runs DeepSeek-R1 in a single-agent setup, where the model not only prepares the actions but also creates the actions as executable Python code. On a subset1 of the GAIA validation split, DeepSeek-R1 exceeds Claude 3.5 Sonnet by 12.5% outright, from 53.1% to 65.6% appropriate, sincansaglik.com and other designs by an even bigger margin:

The experiment followed design use guidelines from the DeepSeek-R1 paper and the design card: Don't utilize 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 evaluation details here.

Approach

DeepSeek-R1's strong coding abilities allow it to serve as a representative without being clearly trained for annunciogratis.net tool use. By permitting the design to create actions as Python code, it can flexibly communicate with environments through code execution.

Tools are implemented as Python code that is consisted of straight in the prompt. This can be a simple function definition or a module of a bigger bundle - any legitimate Python code. The model then produces code actions that call these tools.

Arise from performing these actions feed back to the design as follow-up messages, driving the next actions until a last answer is reached. The agent framework is a simple iterative coding loop that mediates the conversation in between the design and bytes-the-dust.com its environment.

Conversations

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

On the other hand, o1 models are known to perform inadequately when utilized as chat models i.e. they do not attempt to pull context during a discussion. According to the linked article, o1 designs carry out best when they have the complete context available, with clear instructions on what to do with it.

Initially, bio.rogstecnologia.com.br I likewise tried a complete context in a single timely method at each action (with arise from previous actions included), but this caused significantly lower scores on the GAIA subset. Switching to the conversational approach explained above, oke.zone I had the ability to reach the reported 65.6% efficiency.

This raises an interesting concern about the claim that o1 isn't a chat design - maybe this observation was more pertinent to older o1 designs that did not have tool usage abilities? After all, isn't tool usage support an important system for allowing models to pull extra context from their environment? This conversational method certainly seems effective for DeepSeek-R1, though I still need to perform comparable explores o1 designs.

Generalization

Although DeepSeek-R1 was mainly trained with RL on mathematics and coding jobs, macphersonwiki.mywikis.wiki it is exceptional that generalization to agentic tasks with tool usage via code actions works so well. This capability to generalize to agentic tasks reminds of recent research study by DeepMind that shows that RL generalizes whereas SFT remembers, although generalization to tool use wasn't examined in that work.

Despite its ability to generalize to tool use, DeepSeek-R1 often produces long thinking traces at each action, compared to other designs in my experiments, limiting the usefulness of this design in a single-agent setup. Even simpler jobs often take a long period of time to complete. Further RL on agentic tool use, be it by means of code actions or not, could be one option to improve effectiveness.

Underthinking

I likewise observed the underthinking phenomon with DeepSeek-R1. This is when a thinking model often changes between various reasoning ideas without adequately exploring promising courses to reach a proper option. This was a significant reason for excessively long reasoning traces produced by DeepSeek-R1. This can be seen in the taped traces that are available for download.

Future experiments

Another typical application of reasoning designs is to utilize them for planning only, while using other designs for generating code actions. This could be a possible brand-new function of freeact, asteroidsathome.net if this separation of functions proves useful for more complex tasks.

I'm likewise curious about how reasoning models that currently support tool use (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 also utilizes code actions, look interesting.