Tree of Thoughts: Deliberate Problem Solving with Large Language Models · HackerPapers discussions

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by at2005

Mon, 16 Mar 2026 21:47:19 GMT

I didn't compare with the harness (focused on distillation) but the original ToT paper has a section on it: https://arxiv.org/abs/2305.10601

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by ninetyninenine

Wed, 23 Oct 2024 19:36:07 GMT

I have. The failure is with you and your extracting only the mechanical functionality of LLMs as all an LLM is. The high level macro structure of what ends up being trained is something nobody understands. Regardless of WHAT I say, the general consensus among academia and professionals is extremely different from what you characterize. I can cite dozens of research papers contrary to your point in a simple google search: https://www.sciencedirect.com/science/article/pii/S016028962... https://www.topbots.com/llm-reasoning-research-papers/ https://arxiv.org/abs/2305.10601…

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by segmondy

Mon, 16 Sep 2024 00:37:14 GMT

This is not even remotely close and very silly. A ChainOfThought in a loop. TreeOfThoughts is a more sophisticated method, see - https://arxiv.org/pdf/2305.10601 The clue we all had with OpenAI for a long time that this was a search through a tree, they hired Noam Brown, and his past work all hinted towards that. Q, is obviously a search on a tree like A. So take something like CoT, build out a tree, search for the best solution across it. The search is the "system-2 reasoning"

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by richardw

Thu, 23 Nov 2023 05:31:36 GMT

On backtracking, I thought tree-of-thought enabled that? "considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices" https://arxiv.org/abs/2305.10601 Generally with you though, this thing is not leading to real smarts and that's accepted by many. Yes, it'll fill in a few gaps with exponentially more compute but it's more likely that an algo change is required once we've maxed out LLM's.

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by heliophobicdude

Thu, 13 Jul 2023 15:39:16 GMT

I'm really excited about Gemini. It's supposed to have some sort of planning and problem solving ability[2][3]. If it is like Tree of Thoughts [1], then I'm so hyped! Also take a peek at which institution most of the ToT authors are at. 1: https://arxiv.org/pdf/2305.10601.pdf 2: https://blog.google/technology/ai/google-io-2023-keynote-sun... 3: https://www.wired.com/story/google-deepmind-demis-hassabis-c...

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by krychu

Mon, 10 Jul 2023 07:10:31 GMT

Chain of thought: https://arxiv.org/abs/2201.11903 ReAct: https://arxiv.org/abs/2210.03629 Reflexion: https://arxiv.org/abs/2303.11366 Tree of thoughts: https://arxiv.org/abs/2305.10601 Good video on "Tree of thoughts" which also reviews / puts it in the context of other methods: https://www.youtube.com/watch?v=ut5kp56wW_4 Completion vs conversational interface is something you can read about in the OpenAI API documentation. For the remaining things I don't have single specific pointer at hand.

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by lucubratory

Tue, 27 Jun 2023 07:13:12 GMT

I don't know how far "pure" next-token prediction can go with planning, although I wouldn't count them out until their performance starts noticeably plateauing. But the tree of thought architecture is a very similar concept to what you're discussing, you should definitely give it a read: https://arxiv.org/abs/2305.10601 It's not everything involved in traditional planning, but it may be a framework to use more traditional planning algorithms on LLM output.

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by ehsanu1

Thu, 15 Jun 2023 01:00:11 GMT

Sounds like you want something like tree of thoughts: https://arxiv.org/abs/2305.10601

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by eterevsky

Mon, 05 Jun 2023 09:58:54 GMT

> The goal of stack exchange is to create a repository of question answer pairs of knowledge. The problem here is that generational AI isn't able to create these new pairs. I'm not so sure about that. I think we are quite close to an AI being able to put two and two together to create something marginally new. Maybe not an LLM by itself, but with some high-level iterative/recursive process like this: https://arxiv.org/pdf/2305.10601.pdf. What I'm saying is that no-AI policy maybe made sense in late 2022, but will not necessarily hold in late 2023.

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — HN submission

Thu, 01 Jun 2023 11:00:31 GMT

Tree of Thoughts: Official vs. Wrong Implementation

This is Shunyu, author of Tree oF Thoughts (arxiv.org/abs/2305.10601). The official code to replicate paper results is https://github.com/ysymyth/tree-of-thought-llm Not https://github.com/kyegomez/tree-of-thoughts which according to many who told me, is not right/good implementation of ToT, cannot replicate paper results, and damages the reputation of ToT I explained the situation here: https://twitter.com/ShunyuYao12/status/1663946702754021383 I'd appreciate your help by unstaring his and staring mine, as currently Github and Google searches go to his repo by default, and it has been very…

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by ysymyth

Thu, 01 Jun 2023 10:53:22 GMT

This is Shunyu, author of Tree oF Thoughts (arxiv.org/abs/2305.10601). The official code to replicate paper results is https://github.com/ysymyth/tree-of-thought-llm Not https://github.com/kyegomez/tree-of-thoughts which according to many who told me, is not right/good implementation of ToT, and damages the reputation of ToT I explained the situation here: https://twitter.com/ShunyuYao12/status/1663946702754021383 I'd appreciate your help by unstaring his and staring mine, as currently Github and Google searches go to his repo by default, and it has been very misleading for many users.

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by joshka

Fri, 26 May 2023 22:09:20 GMT

Interestingly a 2 days prior to https://arxiv.org/abs/2305.10601, someone released https://arxiv.org/abs/2305.08291 > Large Language Model Guided Tree-of-Thought > In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel approach aimed at improving the problem-solving capabilities of auto-regressive large language models (LLMs). The ToT technique is inspired by the human mind's approach for solving complex reasoning tasks through trial and error. In this process, the human mind explores the solution space through a tree-like thought process, allowing for backtracking when…

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by flakiness

Fri, 26 May 2023 21:03:58 GMT

Note that the repo author != the paper author. The research itself [1] seems legit. The paper author also wrote a paper called ReAct [2], which is one of the core components of the langchain framework. * [1] https://arxiv.org/abs/2305.10601 * [2] https://arxiv.org/abs/2210.03629

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by dventimihasura

Fri, 26 May 2023 15:57:35 GMT

You buried the lede: https://arxiv.org/pdf/2305.10601.pdf

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by superbiome

Tue, 23 May 2023 13:58:14 GMT

I default to immediately asking GPT4 to review its solution and fix any mistakes it finds. There’s also an interesting paper about providing it guidance that it can make a “tree of thoughts” which allows it to move forward and backwards as it comes up with solutions then present its best solution to you. The paper suggests you can squeeze a lot more performance out of LLM’s (even smaller ones) this way. I’ve been wanting to experiment with my prompting in this fashion: https://arxiv.org/pdf/2305.10601.pdf

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — mentioned by jumploops

Sat, 20 May 2023 18:49:34 GMT

Paper here: https://arxiv.org/pdf/2305.10601.pdf

Paper and discussion history. A mention is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — HN submission

Sat, 20 May 2023 14:43:30 GMT

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

34 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — HN submission

Fri, 19 May 2023 23:38:37 GMT

Tree-of-Thought (ToT), complex and general problem solving with LLMs

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models — HN submission

Fri, 19 May 2023 15:02:59 GMT

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

6 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.