Lowe et al. 2017 - Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Smith & Boyd (1991) criteria are irrelevant across the vast majority of the space of possible agents.claim0.753
  Dismissal of earlier criteria as too narrow.
• Who Is The Creator When Multiple Agents Contributequestion0.752
• Evaluating agentic competence requires benchmarks that test the joint deployment of multiple capabilities in multi-agent environments with conflicting incentives, uncertainty, and economic dynamics.quote0.736
  Motivational statement for the benchmark design philosophy.
• The simple fact that intelligent agents are collectives and do not continue unchanged fulfills a necessary requirement for an open-ended evolution of intelligence.claim0.730
  Connects collective intelligence to evolutionary potential.
• Multi-Agent Reflectionconcept0.729
  Approach using multiple LLM agents for generation and critique, a key prior approach to improving reflection.
• ensemble of agentsconcept0.728
  Probabilistic behaviour of an ensemble used to derive the free-energy principle.
• Park et al. 2023: Generative agents — interactive simulacra of human behaviorconcept0.728
  Paper on LLM-based simulacra of human behaviour; cited as ref 3
• Glaese et al. 2022: Improving alignment of dialogue agents via targeted human judgementsconcept0.727
  Alignment paper cited as example of RLHF fine-tuning technique; ref 19