Partner selection alters opponent distributions in policy-gradient dynamics, promoting cooperation when population variance exists, with a Wiener-process stochastic extension proving a sufficient condition and stationary distribution.
Will systems of llm agents cooperate: An investigation into a social dilemma
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Conflicts between alignment objectives or dilemmas increase attack success rates on LRMs by shifting and overlapping safety and functional neural representations.
LLM agents exhibit emergent covert numerical coordination in canonical game settings under restricted or absent communication, shaping strategic outcomes.
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.
A method infers resilience-promoting reward functions via trajectory scoring and integrates them into MARL, with hybrid incentives shown to reduce collapse in disrupted resource environments.
LLM agents exhibit emergent deception in a sustainability game even without lying permission, with neighbor info increasing attacks while aiding biosphere retention.
citing papers explorer
-
The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection
Partner selection alters opponent distributions in policy-gradient dynamics, promoting cooperation when population variance exists, with a Wiener-process stochastic extension proving a sufficient condition and stationary distribution.
-
Conflicts Make Large Reasoning Models Vulnerable to Attacks
Conflicts between alignment objectives or dilemmas increase attack success rates on LRMs by shifting and overlapping safety and functional neural representations.
-
When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents
LLM agents exhibit emergent covert numerical coordination in canonical game settings under restricted or absent communication, shaping strategic outcomes.
-
Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.
-
Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas
A method infers resilience-promoting reward functions via trajectory scoring and integrates them into MARL, with hybrid incentives shown to reduce collapse in disrupted resource environments.
-
Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game
LLM agents exhibit emergent deception in a sustainability game even without lying permission, with neighbor info increasing attacks while aiding biosphere retention.