DictionaryAgents
Agent
An AI that does not just answer but takes actions, checks the results, and keeps going until the job is done.
Definition
An AI system in which a language model directs its own process and tool use to complete a task, instead of following a fixed code path. Anthropic contrasts agents with workflows, where LLMs and tools are orchestrated through predefined code paths; an agent gathers feedback from its environment (tool results, test output) at each step and decides what to do next.
Example
Asked to fix a failing test, an agent runs npm test, reads the error, edits auth.ts, reruns the tests, and stops when they pass.
Appears in
- When and How Context Rot Appears in Coding Agents: A White-Box Study of Agent Skills in Code AuditingarXiv
- SkillReducer: Optimizing LLM Agent Skills for Token EfficiencyarXiv
- Agent READMEs: An Empirical Study of Context Files for Agentic CodingarXiv
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context ManagementarXiv
- Humanize: Judgement Engineering for Agentic CodingarXiv
- TRACE: TRajectory Attribution for Automated Context EngineeringarXiv