Self-play LLM trajectories form model-specific attractors that asymmetrically influence mixed-play partners' stylistic choices and stances across 7 models and 20 topics.
Corrupted by reasoning: Reasoning language models become free-riders in public goods games.arXiv preprint arXiv:2506.23276
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
PAVE is a four-module architecture (Perception, Assessment, Verdict, Emulation) that enables generative agents to perform legitimate rule violations while preserving authority deference, bounded scope, and post-trigger recovery in multi-agent simulations.
Expanded recall in LLM agents erodes cooperative intent in multi-agent social dilemmas, observed in 18 of 28 model-game settings.
Cooperative profiles from behavioral economics games predict LLM team performance in AI-for-science workflows.
citing papers explorer
-
Attractor States Emerge in Multi-Turn LLM Conversations
Self-play LLM trajectories form model-specific attractors that asymmetrically influence mixed-play partners' stylistic choices and stances across 7 models and 20 topics.
-
PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
PAVE is a four-module architecture (Perception, Assessment, Verdict, Emulation) that enables generative agents to perform legitimate rule violations while preserving authority deference, bounded scope, and post-trigger recovery in multi-agent simulations.
-
The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
Expanded recall in LLM agents erodes cooperative intent in multi-agent social dilemmas, observed in 18 of 28 model-game settings.
-
Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
Cooperative profiles from behavioral economics games predict LLM team performance in AI-for-science workflows.