Article
How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II
•
27
Sambit Mukherjee
sadhaklal
AI & ML interests
None yet
Recent Activity
upvoted an article 3 days ago
How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II liked
a model about 2 months ago
phanerozoic/threshold-xnor liked
a model about 2 months ago
phanerozoic/threshold-nor Organizations
upvoted an article 3 days ago
liked 6 models about 2 months ago
upvoted a collection about 2 months ago
liked 2 models 5 months ago
liked a model 7 months ago
liked 3 datasets 9 months ago
liked a model 9 months ago
liked a Space 9 months ago
Cannot verify my account in discord
➕ 1
10
#37 opened 12 months ago
by
pdjota
commented on Tool Use, Unified 12 months ago
Excellent article. Very clearly written.
I have one question though. It seems that that model replies with either (i) a text response or (ii) a tool call. However, in the original ReAct paper, there is a "Thought" -> "Action" -> "Observation" cycle. In other words, in response to the user's query, the model first outputs a "Thought" followed by an "Action". How do I implement this (i.e., make the model "think" before performing a tool call)?
The following are the original ReAct prompts for HotpotQA (from the official ReAct GitHub repo): https://raw.githubusercontent.com/ysymyth/ReAct/refs/heads/master/prompts/prompts_naive.json
If you examine these prompts, you'll notice that the "thoughts" come before the "actions".
upvoted an article 12 months ago
Article
Tool Use, Unified
•
120
posted an
update 12 months ago
Post
1995
What happens when you combine the Chain of Thought (CoT) reasoning capabilities of LLMs with a heuristic-guided tree search algorithm? In the Tree of Thoughts (ToT) paper, the authors (Yao et al.) have coupled GPT-4 with tree search algorithms to attack a few tasks on which left-to-right CoT struggles. And the results are impressive. For example, on the "Game of 24" task, while GPT-4 with CoT prompting only managed to solve 4% of tasks, ToT achieved a success rate of 74%.
I've written a blog post that makes the ToT paper easy to understand and implement by taking you through all the details in a step-by-step manner: https://huggingface.co/blog/sadhaklal/tree-of-thoughts
If you are interested in the topics of algorithmic AI, tree search, reasoning, planning, or "System 2" thinking, then you may find this blog post useful.
I've written a blog post that makes the ToT paper easy to understand and implement by taking you through all the details in a step-by-step manner: https://huggingface.co/blog/sadhaklal/tree-of-thoughts
If you are interested in the topics of algorithmic AI, tree search, reasoning, planning, or "System 2" thinking, then you may find this blog post useful.