nexuschemicalsystems

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 impressed by initial outcomes. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not only prepares the actions but likewise develops 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% correct, and other models by an even bigger margin:

The experiment followed design use standards from the DeepSeek-R1 paper and the design card: Don't utilize few-shot examples, prevent including a system timely, and set the temperature level to 0.5 - 0.7 (0.6 was used). You can discover further assessment details here.

Approach

DeepSeek-R1's strong coding abilities enable it to serve as a representative without being explicitly trained for tool usage. By permitting the model to generate actions as Python code, it can flexibly connect with environments through code execution.

Tools are implemented as Python code that is consisted of straight in the timely. This can be a basic function meaning or a module of a larger bundle - any valid Python code. The model then produces code actions that call these tools.

Results from these actions feed back to the design as follow-up messages, driving the next steps until a last answer is reached. The agent framework is an easy iterative coding loop that mediates the conversation between the model and its environment.

Conversations

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

On the other hand, o1 models are understood to perform improperly when used as chat designs i.e. they don't try to pull context during a discussion. According to the linked post, o1 designs carry out best when they have the complete context available, with clear instructions on what to do with it.

Initially, I likewise attempted a complete context in a single timely approach at each action (with results from previous actions included), but this led to substantially lower scores on the GAIA subset. Switching to the conversational method explained above, I was able to reach the reported 65.6% performance.

This raises a fascinating concern about the claim that o1 isn't a chat model - possibly this observation was more pertinent to older o1 designs that did not have tool usage capabilities? After all, isn't tool use support an important system for making it possible for designs to pull additional context from their environment? This conversational technique certainly appears effective for DeepSeek-R1, though I still need to conduct comparable try outs o1 models.

Generalization

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

Despite its capability to generalize to tool use, DeepSeek-R1 typically produces really long thinking traces at each step, compared to other designs in my experiments, restricting the usefulness of this design in a single-agent setup. Even easier jobs often take a long time to complete. Further RL on agentic tool use, be it by means of code actions or not, might be one choice to enhance performance.

Underthinking

I also observed the underthinking phenomon with DeepSeek-R1. This is when a reasoning model frequently switches in between different reasoning ideas without adequately checking out appealing paths to reach an appropriate option. This was a significant factor for extremely long reasoning traces produced by DeepSeek-R1. This can be seen in the tape-recorded traces that are available for download.

Future experiments

Another common application of thinking designs is to utilize them for preparing only, while using other designs for oke.zone producing code actions. This might be a possible new feature of freeact, if this separation of roles proves beneficial for more complex jobs.

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