Why AI Agent Collectives Need an Interactionist Lens

Kari Jaaskelainen

16 Jan 2026 — 1 min read

When AI agents team up, surprising things happen

Large language models don’t start from scratch. They arrive preloaded with vast knowledge and social priors, and they adapt quickly from context. When many such agents interact, their group behavior can surprise us—for better or worse. A new paper argues we need an interactionist paradigm to study how prior knowledge and embedded values meet social context to shape what emerges.

The authors outline four priorities for research and deployment of LLM-based collectives:

Theory: Build models linking agents’ priors, roles, and interaction patterns to group outcomes.
Methods: Create experiments, benchmarks, and tools to detect, measure, and reproduce emergent behavior.
Governance: Assess risks and benefits and design safeguards at the multi-agent system level.
Trans-disciplinary dialogue: Connect AI with social sciences, ethics, and policy to steer development.

Understanding collective AI is how we harness coordination and creativity while managing bias, manipulation, and failure.

Paper: arxiv.org/abs/2601.10567

Paper: https://arxiv.org/abs/2601.10567v1

Register: https://www.AiFeta.com

#AI #LLM #MultiAgent #CollectiveBehavior #AIResearch #AISafety #Ethics #Society #HCI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

When AI agents team up, surprising things happen

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A