From Circuits to Policies: A Review and Taxonomy of Decision Making and Strategy Selection in LLMs and LLM Agents

Source abstract

Large language models and the agents built on them can reach the same outcome through different internal computations, reasoning trajectories, and system-level policies. Existing reviews typically treat mechanistic interpretability, reasoning, agent architectures, and safety separately, leaving no common framework for analyzing how a system represents alternatives, evaluates them, commits to one, executes it, and revises that choice. This article presents a structured review and a faceted taxonomy of decision making and strategy selection in LLMs and LLM-based agents. The framework distinguishes four loci—model-internal computation, reasoning traces, agent trajectories, and the surrounding system harness—and decomposes decision making into six functional stages from state representation to update or termination. A five-level evidential relation distinguishes behavioral observation, representation decoding, causal influence, controlled manipulation, and mechanistic explanation, while robustness is assessed separately across prompts, tasks, models, and independent replication. Across the literature, evidence is strongest for local mechanisms within individual model calls and substantially weaker for persistent strategies across agent trajectories. The central unresolved gap is cross-locus continuity: few studies follow the same decision variable from internal representation through commitment, executed action, and subsequent feedback. A July 2026 agent-security incident is used to illustrate how the framework converts observed coordination and constraint circumvention into testable causal hypotheses.