







Two LLM agents share a side in 4-player Pokémon Showdown battles and can talk before every turn. Does talking win more battles, and what does it cost?
[Keynote 06] Testing LLM Cooperation in Multi Agent Simulation

Group size effects and collective misalignment in LLM multi-agent systems
Multi-agent systems of large language models (LLMs) are rapidly expanding across domains, introducing dynamics not captured by single-agent evaluations. Yet, existing work has mostly contrasted the behavior of a single agent with that of a collective of fixed size, leaving open a central question: How does group size shape dynamics? Here, we move beyond this dichotomy and systematically explore outcomes across the full range of group sizes. We focus on multi-agent misalignment, building on recent evidence that interacting LLMs playing a simple coordination game can generate collective biases absent in individual models. First, we show that collective bias is a deeper phenomenon than previously assessed: Interaction can amplify individual biases, introduce new ones, or override model-level preferences. Second, we demonstrate that group size affects the dynamics in a nonlinear way, revealing model-dependent dynamical regimes. Finally, we develop a mean-field analytical approach and show that, above a critical population size, simulations converge to deterministic predictions that expose the basins of attraction of competing equilibria. These findings establish group size as a key driver of multi-agent dynamics and highlight the need to consider population-level effects when deploying LLM-based systems at scale.
Mesh-LLM/mesh-llm
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
Multi Model Training for Multi Agent Communication Skills
LLMs and reinforcement learning
My reflection on the Richard Sutton interview with Dwarkesh Patel was that it was interesting how much the two participants talk past each other, and fail to find common ground....

Adversarial Communication
“AI” turns every conversation into a fight, because fighting is what they are good at.
Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Info Ops

LLM Agents are simply Graph — Tutorial For Dummies
Ever wondered how AI agents actually work behind the scenes?

LLM Agents are simply Graph — Tutorial For Dummies
Ever wondered how AI agents actually work behind the scenes?


LLMs and people both learn to form conventions -- just not with each other
Humans align to one another in conversation -- adopting shared conventions that ease communication. We test whether LLMs form the same kinds of conventions in a multimodal communication game. Both humans and LLMs display evidence of convention-formation (increasing the accuracy and consistency of their turns while decreasing their length) when communicating in same-type dyads (humans with humans, AI with AI). However, heterogenous human-AI pairs fail -- suggesting differences in communicative tendencies. In Experiment 2, we ask whether LLMs can be induced to behave more like human conversants, by prompting them to produce superficially humanlike behavior. While the length of their messages matches that of human pairs, accuracy and lexical overlap in human-LLM pairs continues to lag behind that of both human-human and AI-AI pairs. These results suggest that conversational alignment requires more than just the ability to mimic previous interactions, but also shared interpretative biases toward the meanings that are conveyed.


Agent teams perform better when they communicate This paper shows that giving each agent a sendMessage tool allows even weak agents to perform significantly better than running the same LLM K times in isolation A punch to the gut for GPT-Pro, DeepThink, etc models arxiv.org/pdf/2609.21032