telligentmedia

I ran a investigating how DeepSeek-R1 carries out on agentic tasks, regardless of not supporting tool usage natively, and I was quite impressed by initial results. This experiment runs DeepSeek-R1 in a single-agent setup, where the design not only prepares the actions however likewise develops the actions as executable Python code. On a subset1 of the GAIA recognition split, DeepSeek-R1 outperforms Claude 3.5 Sonnet by 12.5% outright, from 53.1% to 65.6% proper, clashofcryptos.trade and wiki.myamens.com other designs by an even bigger margin:

The experiment followed model usage standards from the DeepSeek-R1 paper and dokuwiki.stream the design card: Don't utilize few-shot examples, prevent adding a system timely, and set the temperature to 0.5 - 0.7 (0.6 was used). You can find additional evaluation details here.

Approach

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

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

Arise from executing these actions feed back to the design as follow-up messages, driving the next actions till a last response is reached. The representative framework is a basic iterative coding loop that mediates the discussion between the design and its environment.

Conversations

DeepSeek-R1 is used as chat design in my experiment, where the model autonomously pulls additional context from its environment by using tools e.g. by using a search engine or fishtanklive.wiki fetching information from web pages. This drives the discussion with the environment that continues until a final answer is reached.

In contrast, o1 designs are known to carry out improperly when used as chat models i.e. they do not try to pull context during a conversation. According to the linked article, o1 designs carry out best when they have the full context available, with clear directions on what to do with it.

Initially, I likewise tried a full context in a single timely method at each step (with outcomes from previous steps included), however this caused significantly lower ratings on the GAIA subset. Switching to the conversational approach explained above, I was able to reach the reported 65.6% performance.

This raises a fascinating question about the claim that o1 isn't a chat model - possibly this observation was more pertinent to older o1 designs that lacked tool usage capabilities? After all, classihub.in isn't tool usage support an essential mechanism for enabling models to pull additional context from their environment? This conversational technique certainly seems effective for DeepSeek-R1, though I still need to conduct similar explores o1 designs.

Generalization

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

Despite its ability to generalize to tool use, DeepSeek-R1 often produces very long reasoning traces at each action, compared to other designs in my experiments, limiting the effectiveness of this design in a single-agent setup. Even easier jobs sometimes take a long period of time to complete. Further RL on agentic tool use, be it via code actions or not, might be one alternative to improve effectiveness.

Underthinking

I also observed the underthinking phenomon with DeepSeek-R1. This is when a reasoning model regularly changes in between different thinking thoughts without adequately exploring promising courses to reach a proper service. This was a major factor for overly long thinking 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 reasoning models is to use them for preparing just, while using other models for producing code actions. This might be a possible brand-new function of freeact, if this separation of roles shows beneficial for more complex jobs.

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