7 pages tagged

#reasoning

agent-loop concept The ~20-line ReAct loop; Workflow vs Agent; five control patterns; loop as optimization target. chain-of-thought concept CoT "think step by step" + Tree of Thoughts; test-time compute; ancestor of reasoning models. react concept Reasoning + Acting; the bridge that lets language priors generalize across RL environments. reasoning-models concept o1 / R1 paradigm; the second scaling axis (inference compute); effort as the user-facing dial. self-reflection concept Reflexion / Chain of Hindsight / Algorithm Distillation; ancestor of verifier + ralph-wiggum loops. task-decomposition concept Planning by subgoals: CoT, Tree of Thoughts, LLM+P; the decomposition half of agent Planning. 2026-04-27-the-second-half-of-ai source Shunyu Yao's thesis: the recipe generalizes; evaluation is the bottleneck — the utility problem.
esc