# Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates

arXiv: https://arxiv.org/abs/2607.01047 · HTML: https://mlsanity.com/paper/2607.01047/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 74 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 33)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [Let's Think Dot by Dot: Hidden Computation in Transformer Language Models](https://mlsanity.com/paper/2404.15758/) (2024)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://mlsanity.com/paper/1803.03453/) (2018)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents](https://mlsanity.com/paper/1903.00784/) (2019)
- [Lenia - Biology of Artificial Life](https://mlsanity.com/paper/1812.05433/) (2018)
- [Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations](https://mlsanity.com/paper/2505.13763/) (2025)
- [Agents of Chaos](https://mlsanity.com/paper/2602.20021/) (2026)
- [Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity](https://mlsanity.com/paper/2510.27378/) (2025)
- [Because we have LLMs, we Can and Should Pursue Agentic Interpretability](https://mlsanity.com/paper/2506.12152/) (2025)
- [Towards Compositional Interpretability for XAI](https://mlsanity.com/paper/2406.17583/) (2024)
- [Flow-Lenia: Towards open-ended evolution in cellular automata through mass conservation and parameter localization](https://mlsanity.com/paper/2212.07906/) (2022)
- [Collective Innovation in Groups of Large Language Models](https://mlsanity.com/paper/2407.05377/) (2024)
- [Spore in the Wild: A Case Study of Spore.fun as an Open-Environment Evolution Experiment with Sovereign AI Agents on TEE-Secured Blockchains](https://mlsanity.com/paper/2506.04236/) (2025)
- [Generative AI collective behavior needs an interactionist paradigm](https://mlsanity.com/paper/2601.10567/) (2026)

## Built on by (most cited first, 1 of 1)

- [Xeno-Interpretability: Investigating the Alien Minds of LLMs](https://mlsanity.com/paper/2609.20408/) (2026)

## Abstract (arXiv)

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 agentic. In this paper, we argue that such collectives of agents can serve as a computational substrate for Artificial Life (ALife) research. Critically, since the agents communicate in natural language, their collective behaviour can be directly interrogated by examining textual traces and asking the agents themselves. We outline the notion of interpretability in language-model research and extend it for collectives of agents. Lastly, we survey recent examples of agentic LLM collectives that already instantiate the idea of agentic substrates, from controlled experiments to deployments in the wild.