I ran a fast experiment examining how DeepSeek-R1 performs on agentic tasks, despite not supporting tool usage natively, and imoodle.win I was quite satisfied by preliminary outcomes. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not only plans the actions but also creates the actions as executable Python code. On a subset1 of the GAIA validation split, DeepSeek-R1 surpasses Claude 3.5 Sonnet by 12.5% outright, from 53.1% to 65.6% appropriate, and other models by an even bigger margin:

The experiment followed model usage guidelines from the DeepSeek-R1 paper and the model card: Don't utilize few-shot examples, prevent adding a system prompt, and set the temperature level to 0.5 - 0.7 (0.6 was utilized). You can find more examination details here.

Approach

DeepSeek-R1's strong coding capabilities enable it to serve as an agent without being explicitly trained for disgaeawiki.info tool use. By enabling the design to create 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 a basic function definition or a module of a bigger bundle - any valid Python code. The model then generates code actions that call these tools.

Arise 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 framework is an easy iterative coding loop that mediates the conversation between the design and wiki.vst.hs-furtwangen.de its environment.

Conversations

DeepSeek-R1 is used as chat model in my experiment, where the model autonomously pulls additional context from its environment by utilizing tools e.g. by using an online search engine or fetching data from websites. This drives the conversation with the environment that continues till a last response is reached.

On the other hand, o1 models are understood to carry out poorly when as chat designs i.e. they do not attempt to pull context during a conversation. According to the connected article, o1 designs 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 timely method at each action (with arise from previous steps consisted of), higgledy-piggledy.xyz however this led to significantly lower scores on the GAIA subset. Switching to the conversational technique explained above, I had the ability to reach the reported 65.6% efficiency.

This raises an intriguing concern about the claim that o1 isn't a chat design - maybe this observation was more pertinent to older o1 designs that lacked tool use capabilities? 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 efficient for yewiki.org DeepSeek-R1, though I still require to perform similar experiments with o1 models.

Generalization

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

Despite its capability to generalize to tool usage, DeepSeek-R1 often produces long thinking traces at each step, compared to other models in my experiments, restricting the usefulness of this design in a single-agent setup. Even simpler tasks in some cases take a very long time to finish. Further RL on agentic tool use, be it by means of code actions or setiathome.berkeley.edu not, might be one option to improve efficiency.

Underthinking

I likewise observed the underthinking phenomon with DeepSeek-R1. This is when a reasoning model regularly switches between various thinking ideas without sufficiently exploring appealing courses to reach an appropriate solution. This was a major reason for overly 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 models is to use them for planning only, while using other designs for creating code actions. This might be a prospective brand-new feature of freeact, if this separation of roles proves useful for more complex jobs.

I'm also curious about how reasoning designs that currently support tool usage (like o1, o3, ...) carry out in a single-agent setup, engel-und-waisen.de with and without producing code actions. Recent developments like OpenAI's Deep Research or Hugging Face's open-source Deep Research, which likewise uses code actions, look fascinating.