Reasoning Concepts

Chain of thought is the technique of having a language model write out its intermediate reasoning before answering. Reasoning models extend it by training the model with reinforcement learning to think at length before responding.

AGI is the goal of AI systems that match or beat humans across a broad range of tasks. The term has no agreed definition; a framework by Morris et al. grades systems by performance level and generality.

Test-time compute is the computation a model spends while answering a prompt, beyond what training already fixed into its weights. A 2024 study by Snell et al. showed how to spend it adaptively, and how it can stand in for a bigger model.

Tool calling lets a language model hand a sub-task, such as arithmetic or search, to an external program and use the result in its answer. Toolformer showed in 2023 that a model could learn when and how to call tools on its own.

Planning in AI agents is the process of breaking a goal into intermediate steps, choosing actions, and revising the plan as results arrive, rather than producing an answer in one pass.[^1][^2]

Reward hacking is what happens when a system optimises a proxy reward that only imperfectly captures what we want: it scores well on the proxy while performing badly on the true objective.

Prompt engineering is the practice of designing the text input that steers a generative AI system toward a desired output. Shared vocabulary and techniques such as chain-of-thought prompting make results easier to describe, compare and reproduce.