Agent

What it is

The system implements a loop where the LLM evaluates the current state, selects a tool from a defined registry, and executes the call. It interprets the tool output to determine the next step or whether the final goal is met. These loops typically involve 3 to 10 sequential model calls per user request, significantly increasing the latency and cost per transaction compared to a single-shot prompt. Managing the persistent state across these steps is the primary architectural requirement for agentic systems.

Why it matters

Moving from static prompts to agents shifts your architecture from request-response to stateful long-running workflows. You must manage complex error handling, infinite loop detection, and cost spikes caused by excessive model calls. If you ignore these dynamics, you will likely hit API rate limits and experience silent failures where the agent gets stuck in a recursive loop without the user knowing.

In practice

In production, you monitor the agent by tracking the number of steps per trace and the cumulative token usage for each request. You will frequently tune the system prompt and the tool descriptions to minimize unnecessary calls, often using observability tools to debug the reasoning chain within the agent's loop.

The tradeoff

The main tradeoff is that increasing agent autonomy improves performance on complex tasks but drastically reduces predictability and increases the surface area for hallucinations.

Where it appears

Research summaries that use Agent, each linked to its source paper.

• Improving AI Terminal Task Construction
  CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

  CalibForge uses automated adversarial feedback from software solvers to ensure that training tasks for LLM agents are neither too simple nor impossible to solve.

• Fixing Stale Spatial Memory in AI Agents
  When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents

  The paper introduces a read-time filtering intervention called OMCD to prevent vision-language model agents from making fatal navigation errors caused by outdated spatial knowledge.

• A New Way to Fix AI Agent Failures
  Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures

  The researchers developed a new classification system that identifies exactly which part of an artificial intelligence agent caused a mistake, making it easier to fix errors.