Exploring DeepSeek-R1’s Agentic Capabilities Through Code Actions

I ran a quick experiment examining how DeepSeek-R1 performs on agentic jobs, despite not supporting tool use natively, and I was quite impressed by preliminary results. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not just prepares the actions but 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% outright, from 53.1% to 65.6% right, akropolistravel.com and archmageriseswiki.com other designs by an even bigger margin:

The experiment followed model usage guidelines from the DeepSeek-R1 paper and the model card: Don’t use few-shot examples, avoid adding a system prompt, and set the temperature to 0.5 – 0.7 (0.6 was utilized). You can discover additional examination details here.

Approach

DeepSeek-R1‘s strong coding capabilities allow 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 executed as Python code that is included straight in the timely. This can be an easy function meaning or a module of a bigger package – any valid Python code. The model then creates code actions that call these tools.

Results from performing these actions feed back to the model as follow-up messages, driving the next actions until a final answer is reached. The representative structure is a basic iterative coding loop that mediates the discussion between the design and oke.zone 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 an online search engine or bring information from web pages. This drives the conversation with the environment that continues until a final answer is reached.

In contrast, o1 models are understood to carry out badly when used as chat designs i.e. they don’t try to pull context throughout a conversation. According to the connected article, o1 models perform best when they have the full context available, with clear guidelines on what to do with it.

Initially, I also attempted a complete context in a single prompt approach at each step (with results from previous actions included), however this resulted in considerably lower ratings on the GAIA subset. Switching to the conversational technique explained above, wiki.myamens.com I was able to reach the reported 65.6% performance.

This raises a fascinating question about the claim that o1 isn’t a chat design – maybe this observation was more appropriate to older o1 models that did not have tool usage abilities? After all, isn’t tool use support a crucial system for making it possible for designs to pull extra context from their environment? This conversational technique certainly appears reliable for DeepSeek-R1, asteroidsathome.net though I still require to perform comparable explores o1 designs.

Generalization

Although DeepSeek-R1 was mainly trained with RL on mathematics and coding jobs, it is impressive that generalization to agentic tasks with tool use through code actions works so well. This ability to generalize to agentic tasks reminds of recent research by DeepMind that shows that RL generalizes whereas SFT remembers, although generalization to tool use wasn’t examined because work.

Despite its ability to generalize to tool use, DeepSeek-R1 frequently produces very long thinking traces at each action, compared to other models in my experiments, restricting the usefulness of this design in a single-agent setup. Even simpler jobs often take a very long time to complete. Further RL on agentic tool use, be it via code or not, could be one alternative to enhance effectiveness.

Underthinking

I likewise observed the underthinking phenomon with DeepSeek-R1. This is when a thinking model often changes between different reasoning ideas without adequately checking out promising paths to reach a correct option. This was a major 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 models is to utilize them for preparing only, while using other models for producing code actions. This could be a potential brand-new feature of freeact, if this separation of functions shows beneficial for more complex tasks.

I’m also curious about how reasoning designs that already support tool use (like o1, wifidb.science o3, …) carry out in a single-agent setup, with and without creating code actions. Recent advancements like OpenAI’s Deep Research or larsaluarna.se Hugging Face’s open-source Deep Research, which also utilizes code actions, look fascinating.