Hello, I'm Shrijith Venkatramana, and I'm building LiveReview — a blast-radius aware AI code review built for your business-critical systems. Star us to help devs discover the project, give it a try, and share your feedback to help improve the product.
The model can be extremely capable, yet once it commits to a bad intermediate step, everything downstream is built on top of it.
Ask a model to solve a difficult planning problem and you often get something that looks intelligent but fails because of one early mistake:
"What if I try this approach?" "That looks bad. Back up." "What happens if I choose the other interpretation?" "This branch is promising. Explore it further."
That idea leads to Tree of Thoughts (ToT) and, more ambitiously, to Monte Carlo Tree Search (MCTS)-style reasoning for LLMs.
And that turns out to be a surprisingly important architectural shift. From Chain of Thought to Search
The easiest way to understand Tree of Thoughts is to compare it with ordinary Chain of Thought.
The problem is obvious: once it walks down this path, it is stuck with its earlier choices.
A Tree-of-Thought system instead treats intermediate reasoning as search states.
The LLM is no longer merely generating a sequence. It is generating candidates for the next state and evaluating which states deserve more exploration.
The 2023 Tree-of-Thoughts paper by Shunyu Yao and colleagues made this framing explicit: instead of reasoning token-by-token, the model can operate over coherent intermediate "thoughts", explore alternatives, evaluate them, and backtrack.
The famous result from their Game of 24 experiment illustrates why this matters. Their GPT-4 chain-of-thought baseline solved only about 4% of instances, while their Tree-of-Thoughts procedure reached 74%. The exact numbers are task-specific, but the conceptual point is much bigger: search can compensate for the brittleness of a single sampled reasoning trajectory. ([arXiv][1])
If you've seen the 2016 AlphaGo story, you have already seen the basic architecture.
AlphaGo was developed by David Silver, Demis Hassabis and a large DeepMind team. It combined neural networks with Monte Carlo Tree Search to reason over possible Go positions.
The game has an enormous branching factor. A purely enumerative search is hopeless.
The result was one of the most memorable moments in AI history: in March 2016, AlphaGo defeated Lee Sedol 4-1. One of the moves from that match, move 37 in game 2, became famous because it was so unlike what human professionals expected.
The original AlphaGo work explicitly described a system that combined policy/value networks with Monte Carlo tree search, and later AlphaZero generalized the idea even further through self-play. ([DOI][2]) What a "Thought" Actually Is
The language model itself can become both the proposal mechanism and the heuristic.