I ran a quick experiment examining how DeepSeek-R1 carries out on agentic tasks, despite not supporting tool use natively, and I was quite pleased by initial outcomes. 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 recognition split, DeepSeek-R1 exceeds Claude 3.5 Sonnet by 12.5% absolute, from 53.1% to 65.6% appropriate, and townshipmarket.co.za other models by an even larger margin:
The experiment followed design use guidelines from the DeepSeek-R1 paper and photorum.eclat-mauve.fr the design card: Don't utilize few-shot examples, prevent adding a system timely, and set the temperature level to 0.5 - 0.7 (0.6 was utilized). You can find more assessment details here.
Approach
DeepSeek-R1's strong coding allow it to serve as a representative without being explicitly trained for tool usage. By allowing the design to generate actions as Python code, it can flexibly interact with environments through code execution.
Tools are executed as Python code that is consisted of straight in the prompt. This can be a simple function meaning or a module of a bigger bundle - any legitimate Python code. The design then creates code actions that call these tools.
Results from performing these actions feed back to the design as follow-up messages, driving the next steps until a final answer is reached. The agent structure is a basic iterative coding loop that moderates the conversation in between the model 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 utilizing tools e.g. by using a search engine or fetching information from websites. This drives the conversation with the environment that continues until a last answer is reached.
On the other hand, o1 models are understood to perform badly when used as chat models i.e. they do not attempt to pull context throughout a conversation. According to the connected short article, o1 designs perform best when they have the full context available, with clear guidelines on what to do with it.
Initially, I likewise attempted a full context in a single prompt approach at each action (with arise from previous steps included), but this led to considerably lower ratings on the GAIA subset. Switching to the conversational technique explained above, I had the ability to reach the reported 65.6% efficiency.
This raises a fascinating question about the claim that o1 isn't a chat design - maybe this observation was more pertinent to older o1 models that lacked tool usage abilities? After all, isn't tool usage support an essential system for making it possible for models to pull additional context from their environment? This conversational method certainly seems reliable for DeepSeek-R1, though I still require to conduct comparable experiments with o1 designs.
Generalization
Although DeepSeek-R1 was mainly trained with RL on mathematics and coding jobs, photorum.eclat-mauve.fr it is amazing that generalization to agentic tasks with tool usage via code actions works so well. This ability to generalize to agentic jobs advises of current research study by DeepMind that shows that RL generalizes whereas SFT remembers, forum.altaycoins.com although generalization to tool use wasn't examined because work.
Despite its capability to generalize to tool use, DeepSeek-R1 often produces very long reasoning traces at each step, compared to other designs in my experiments, limiting the usefulness of this model in a single-agent setup. Even simpler jobs often take a very long time to finish. Further RL on agentic tool use, trademarketclassifieds.com be it by means of code actions or not, might be one alternative to enhance effectiveness.
Underthinking
I likewise observed the underthinking phenomon with DeepSeek-R1. This is when a thinking design often switches between different thinking thoughts without adequately exploring promising paths to reach a correct option. This was a significant factor for overly long thinking 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 designs is to utilize them for planning only, while utilizing other models for creating code actions. This might be a prospective brand-new function of freeact, if this separation of functions shows useful for more complex jobs.
I'm also curious about how thinking models that currently support tool usage (like o1, o3, ...) carry out in a single-agent setup, with and without producing code actions. Recent advancements like OpenAI's Deep Research or Hugging Face's open-source Deep Research, which likewise utilizes code actions, look interesting.
1
Exploring DeepSeek-R1's Agentic Capabilities Through Code Actions
Ada Koehler edited this page 2025-02-12 06:25:57 +08:00