More capable LLMs and agents generate code with greater volume and architectural decay, following a Volume-Quality Inverse Law that neither functional correctness nor prompting mitigates.
International Conference on Learning Representations, ICLR
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
FSTS automates multi-agent social experiment design via LLM script generation across three phases, with tests indicating reproduction of real-world outcomes.
citing papers explorer
-
AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
More capable LLMs and agents generate code with greater volume and architectural decay, following a Volume-Quality Inverse Law that neither functional correctness nor prompting mitigates.
-
From Script to Stage: Automating Experimental Design for Social Simulations with LLMs
FSTS automates multi-agent social experiment design via LLM script generation across three phases, with tests indicating reproduction of real-world outcomes.