Reasoning

Reverse-Process Synthetic Data Generation for Math Reasoning

Training LLMs on mathematical reasoning by inverting easy-to-solve problems: generate derivatives, reverse them into integration exercises with full step-by-step solutions.

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Notes

Step-by-step reasoning via prompting. Unlocked a new capability class.

ReAct: Synergizing Reasoning and Acting in Language Models

Notes

Interleaving reasoning traces and actions. The prompting pattern behind most LLM agents.

Superintelligence May Not Require a Breakthrough

The most dramatic possibility in AI might arrive through the most mundane mechanism. Not a beam of sacred light. A sufficiently good build system.

Value Functions Over Reasoning Traces

What if reasoning traces could learn their own usefulness? A simple RL framing for trace memory, and why one reward signal is enough.

MCTS-Reasoning: Tree Search for LLM Reasoning

Applying Monte Carlo Tree Search to large language model reasoning, with a formal specification of the algorithm.

Latent Reasoning Traces: Memory as Learned Prior

What if LLMs could remember their own successful reasoning? A simple experiment in trace retrieval, and why 'latent' is the right word.