LLM-as-Code: Agentic Programming for Agent Harness

The point

A paper proposes Agentic Programming, where the program governs control flow and the model is called only for reasoning or generation. The authors argue token explosion, control flow hallucination and unreliable completion follow from letting a probabilistic model handle looping, branching and sequencing.

Why it matters

For builders, control in code could make agent runs more reliable.

Key details

Original ~5 min → 25 sec here Source: arXiv cs.AI, Nov 9, 2026

← All points