arXiv AI
How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 26
Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems
arXiv:2606. 07552v2 Announce Type: replace-cross Abstract: Large language models exhibit a risk-averse "turtle" bias as strategic agents.
arXiv AI
Jun 9
Payoff scaling shapes cooperation in LLM agents across languages
arXiv:2601. 19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users.
arXiv AI
Jul 2
Large language models replicate and predict human cooperation across experiments in game theory
arXiv:2511. 04500v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in high-stakes domains and as imitators of human behavior in the social and behavioral sciences.
arXiv AI
Jun 9
Symbolic Reasoning Frameworks Modulate LLM Risk Aversion in Multi-Agent Strategic Settings
arXiv:2606. 07552v1 Announce Type: cross Abstract: Large language models exhibit innate behavioral tendencies when deployed as strategic agents -- notably a risk-averse "turtle" bias toward defensive play.
arXiv AI
Jul 7
They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It
arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
arXiv Machine Learning
Aug 4
Training Small LLMs as Spatial Multi-Agent Policies
arXiv:2608. 01425v1 Announce Type: cross Abstract: Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that such systems should be judged by their behavior, not only their reward.