signspublishing

I ran a fast experiment investigating how DeepSeek-R1 performs on agentic jobs, regardless of not supporting tool usage natively, and I was quite pleased by initial results. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not only prepares the actions however likewise formulates the actions as executable Python code. On a subset1 of the GAIA recognition split, DeepSeek-R1 exceeds Claude 3.5 Sonnet by 12.5% outright, from 53.1% to 65.6% right, and other designs by an even larger margin:

The experiment followed model use standards from the DeepSeek-R1 paper and bybio.co the model card: Don't utilize few-shot examples, prevent adding a system prompt, and set the temperature to 0.5 - 0.7 (0.6 was used). You can find further examination details here.

Approach

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

Tools are executed as Python code that is included straight in the timely. This can be an easy function meaning or a module of a bigger plan - any legitimate Python code. The model then creates code actions that call these tools.

Arise from performing these actions feed back to the design 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 its environment.

Conversations

DeepSeek-R1 is used as chat design in my experiment, where the design autonomously pulls extra context from its environment by utilizing tools e.g. by utilizing a search engine or fetching information from websites. This drives the conversation with the environment that continues till a final answer is reached.

On the other hand, o1 models are known to perform inadequately when used as chat models i.e. they do not attempt to pull context throughout a conversation. According to the linked short article, o1 models carry out best when they have the complete context available, with clear directions on what to do with it.

Initially, I also attempted a full context in a single prompt technique at each step (with arise from previous steps included), however this led to considerably lower scores on the GAIA subset. Switching to the conversational technique explained above, I was able to reach the reported 65.6% efficiency.

This raises an intriguing concern about the claim that o1 isn't a chat design - perhaps this observation was more relevant to older o1 models that lacked tool usage abilities? After all, isn't tool usage support an important mechanism for making it possible for designs to pull additional context from their environment? This conversational approach certainly seems effective for DeepSeek-R1, though I still need to carry out 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 usage by means of code actions works so well. This ability to generalize to agentic tasks advises of recent research by DeepMind that shows that RL generalizes whereas SFT remembers, although generalization to tool usage wasn't investigated because work.

Despite its ability to generalize to tool use, DeepSeek-R1 frequently produces extremely long reasoning traces at each step, compared to other models in my experiments, restricting the usefulness of this model in a . Even simpler tasks in some cases take a long time to complete. Further RL on agentic tool usage, be it via code actions or not, might be one alternative to enhance performance.

Underthinking

I likewise observed the underthinking phenomon with DeepSeek-R1. This is when a reasoning design often switches in between different reasoning thoughts without adequately checking out appealing paths to reach a right solution. This was a significant reason for extremely long reasoning 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 producing code actions. This might be a potential brand-new feature of freeact, if this separation of functions proves helpful for more complex tasks.

I'm likewise curious about how reasoning models that already support tool use (like o1, o3, ...) carry out in a single-agent setup, with and without creating code actions. Recent advancements like OpenAI's Deep Research or Hugging Face's open-source Deep Research, wiki.vst.hs-furtwangen.de which likewise utilizes code actions, look interesting.