@ -6,7 +6,7 @@ import TOT from '../../img/TOT.png'
import TOT2 from '../../img/TOT2.png'
import TOT3 from '../../img/TOT3.png'
For complex tasks that require exploration or strategic lookahead, traditional or simple prompting techniques fall short. [Yao et el. (2023)](https://arxiv.org/abs/2305.10601) recently proposed Tree of Thoughts (ToT), a framework that generalizes over chain-of-thought prompting and encourages exploration over thoughts that serve as intermediate steps for general problem solving with language models.
For complex tasks that require exploration or strategic lookahead, traditional or simple prompting techniques fall short. [Yao et el. (2023)](https://arxiv.org/abs/2305.10601) and [Long (2023)](https://arxiv.org/abs/2305.08291) recently proposed Tree of Thoughts (ToT), a framework that generalizes over chain-of-thought prompting and encourages exploration over thoughts that serve as intermediate steps for general problem solving with language models.
ToT maintains a tree of thoughts, where thoughts represent coherent language sequences that serve as intermediate steps toward solving a problem. This approach enables an LM to self-evaluate the progress intermediate thoughts make towards solving a problem through a deliberate reasoning process. The LM ability to generate and evaluate thoughts is then combined with search algorithms (e.g., breadth-first search and depth-first search) to enable systematic exploration of thoughts with lookahead and backtracking.
@ -27,4 +27,7 @@ From the results reported in the figure below, ToT substantially outperforms the
<Screenshot src={TOT3} alt="TOT3" />
Image Source: [Yao et el. (2023)](https://arxiv.org/abs/2305.10601)
Code available [here](https://github.com/princeton-nlp/tree-of-thought-llm)
Code available [here](https://github.com/princeton-nlp/tree-of-thought-llm) and [here](https://github.com/jieyilong/tree-of-thought-puzzle-solver)
At a high level, the main ideas of [Yao et el. (2023)](https://arxiv.org/abs/2305.10601) and [Long (2023)](https://arxiv.org/abs/2305.08291) are similar. Both enhance LLM's capability for complex problem solving through tree search via a multi-round conversation. One of the main difference is that [Yao et el. (2023)](https://arxiv.org/abs/2305.10601) leverages DFS/BFS/beam search, while the tree search strategy (i.e. when to backtrack and backtracking by how many levels, etc.) proposed in [Long (2023)](https://arxiv.org/abs/2305.08291) is driven by a "ToT Controller" trained through reinforcement learning. DFS/BFS/Beam search are generic solution search strategies with no adaptation to specific problems. In comparison, a ToT Controller trained through RL might be able learn from new data set or through self-play (AlphaGo vs brute force search), and hence the RL-based ToT system can continue to evolve and learn new knowledge even with a fixed LLM.