Skip to content
The Nexus
DossierENTITY

LLM agents

Coverage of LLM agents in the Nexus archive.

Earliest in view: May 24 · 12:55 UTCMost recent: Aug 5 · 04:36 UTC
Co-mentioned in this coverage
Recent coverage
  • TECHNOLOGYAug 5 · 04:36 UTCHACKER NEWS
    Zero-Mem: Zero-Token Memory Operations for LLM Agents

    The article introduces 'Zero-Mem', a method enabling zero-token memory operations for large language model (LLM) agents. The approach is detailed in a research paper available on arXiv and discussed on Hacker News with limited engagement.

  • SECURITYJun 5 · 07:43 UTCHACKER NEWS
    Show HN: I benchmarked LLM agents on fixing real-world security vulnerabilities

    A benchmark tested 5 LLM agents on fixing 20 real-world security vulnerabilities across 18 Python projects. The best solve rate was 50%, with cost differences between models (e.g., gpt-5.5 vs. gpt-5.4-mini) outweighing performance gains, likely due to training data variations.

  • SECURITYMay 29 · 19:28 UTCHACKER NEWS
    CVE-Bench: testing LLM agents on real-world vulnerability patches

    CVE-Bench is a benchmark for testing large language model (LLM) agents using real-world vulnerability patches. The article provides a URL for the project and a Hacker News comments link.

  • TECHNOLOGYMay 24 · 12:55 UTCHACKER NEWS
    Constraint Decay: The Fragility of LLM Agents in Back End Code Generation

    The article discusses 'constraint decay' in large language models (LLMs), highlighting their fragility when generating back-end code due to the erosion of imposed constraints. It emphasizes challenges in maintaining reliability and accuracy in automated code generation tasks.