A study reveals that large language model (LLM) agents struggle to handle structural constraints in code generation, leading to a decline in performance as requirements accumulate. The research evaluates the agents' ability to generate code across 100 tasks and 8 web frameworks, identifying data-layer defects as the primary cause of errors.

This article evaluates the use of Large Language Models (LLMs) for generating Entity-Relationship (ER) diagrams from natural language requirements. The study found that LLMs perform well in simple scenarios but struggle with complex ones, leading to inconsistencies and failures in representing constraints. This indicates that LLMs are not yet mature for reliable use in complex conceptual database modeling.

Researchers introduce LSREP, a protocol for evaluating conversational memory, and ICE v2, a local-first memory middleware. The study compares ICE v2 to vector-RAG on four datasets, highlighting its strengths and weaknesses. LSREP and ICE v2 provide insights into conversational memory and its evaluation, which is relevant to people building and operating AI agents.