Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
Complexity and interpretability rarely coincide: systems rich enough for complex behaviours to emerge are usually too opaque to question, while transparent ones are too simple for anything complex to emerge. A single large language model (LLM) is a static artefact, hardly exhibiting any of the emergent properties we associate with life. This changes through interaction: populations of LLMs display emergent dynamics absent from isolated models. Furthermore, LLMs can be endowed with persistent memory, tools and shared skills, and the capacity to initiate actions unprompted, i.e., turning LLMs ag
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorElias Najarro →
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
- Linked via arxiv authorAne Espeseth →
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
- Linked via arxiv authorEleni Nisioti →
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
- Linked via arxiv authorSebastian Risi →
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
- Linked via arxiv authorStefano Nichele →
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates